论文检索

Optimization · Neural Network Optimization

Yehonathan Refael, Guy Smorodinsky, Tom Tirer, Ofir Lindenbaum

Low-rank gradient-based optimization methods have significantly improved memory efficiency during the training of large language models (LLMs), enabling operations within constrained hardware without sacrificing performance. However, these methods primarily emphasize memory savings, often overlooking potential acceleration in convergence due to their reliance on standard isotropic steepest descent techniques, which can perform suboptimally in the highly anisotropic landscapes typical of deep networks, particularly LLMs. In this paper, we propose SUMO (Subspace-Aware Moment-Orthogonalization), an optimizer that employs exact singular value decomposition (SVD) for moment orthogonalization within a dynamically adapted low-dimensional subspace, enabling norm-inducing steepest descent optimization steps. By explicitly aligning optimization steps with the spectral characteristics of the loss landscape, SUMO effectively mitigates approximation errors associated with commonly used methods like Newton-Schulz orthogonalization approximation. We theoretically establish an upper bound on these approximation errors, proving their dependence on the condition numbers of moments, conditions we analytically demonstrate are encountered during LLM training. Furthermore, we both theoretically and empirically illustrate that exact orthogonalization via SVD substantially improves convergence rates while reducing overall complexity. Empirical evaluations confirm that SUMO accelerates convergence, enhances stability, improves performance, and reduces memory requirements by up to 20\% compared to state-of-the-art methods.

Applications · Chemistry and Drug Discovery

Jongha (Jon) Ryu, Samuel Zhou, Gregory Wornell

Spectral decomposition of linear operators plays a central role in many areas of machine learning and scientific computing. Recent work has explored training neural networks to approximate eigenfunctions of such operators, enabling scalable approaches to representation learning, dynamical systems, and partial differential equations (PDEs). In this paper, we revisit a classical optimization framework from the computational physics literature known as the *orbital minimization method* (OMM), originally proposed in the 1990s for solving eigenvalue problems in computational chemistry. We provide a simple linear-algebraic proof of the consistency of the OMM objective, and reveal connections between this method and several ideas that have appeared independently across different domains. Our primary goal is to justify its broader applicability in modern learning pipelines. We adapt this framework to train neural networks to decompose positive semidefinite operators, and demonstrate its practical advantages across a range of benchmark tasks. Our results highlight how revisiting classical numerical methods through the lens of modern theory and computation can provide not only a principled approach for deploying neural networks in numerical simulation, but also effective and scalable tools for machine learning.

Applications · Physics

Arthur Bizzi, Leonardo Moreira, Márcio Marques, Leonardo Mendonça, Christian de Oliveira, Vitor Balestro, Lucas dos Santos Fernandez, Daniel Yukimura, Pavel Petrov, João Pereira 等

Physics-Informed Neural Networks (PINNs) have emerged as a powerful frame- work for solving partial differential equations (PDEs). However, standard MLP- based PINNs often fail to converge when dealing with complex initial value problems, leading to solutions that violate causality and suffer from a spectral bias towards low-frequency components. To address these issues, we introduce NeuSA (Neuro-Spectral Architectures), a novel class of PINNs inspired by classi- cal spectral methods, designed to solve linear and nonlinear PDEs with variable coefficients. NeuSA learns a projection of the underlying PDE onto a spectral basis, leading to a finite-dimensional representation of the dynamics which is then integrated with an adapted Neural ODE (NODE). This allows us to overcome spectral bias, by leveraging the high-frequency components enabled by the spectral representation; to enforce causality, by inheriting the causal structure of NODEs, and to start training near the target solution, by means of an initialization scheme based on classical methods. We validate NeuSA on canonical benchmarks for lin- ear and nonlinear wave equations, demonstrating strong performance as compared to other architectures, with faster convergence, improved temporal consistency and superior predictive accuracy. Code and pretrained models are available in https://github.com/arthur-bizzi/neusa.

Deep Learning · Robustness

Steffen Schotthöfer, Lexie Yang, Stefan Schnake

Deployment of neural networks on resource-constrained devices demands models that are both compact and robust to adversarial inputs. However, compression and adversarial robustness often conflict. In this work, we introduce a dynamical low-rank training scheme enhanced with a novel spectral regularizer that controls the condition number of the low-rank core in each layer. This approach mitigates the sensitivity of compressed models to adversarial perturbations without sacrificing clean accuracy. The method is model- and data-agnostic, computationally efficient, and supports rank adaptivity to automatically compress the network at hand. Extensive experiments across standard architectures, datasets, and adversarial attacks show the regularized networks can achieve over 94 compression while recovering or improving adversarial accuracy relative to uncompressed baselines.

Computer Vision · Image and Video Generation

Guanxiong Luo, Shoujin Huang

We propose ***self-diffusion***, a novel framework for solving inverse problems without relying on pretrained generative models. Traditional diffusion-based approaches require training a model on a clean dataset to learn to reverse the forward noising process. This model is then used to sample clean solutions---corresponding to posterior sampling from a Bayesian perspective---that are consistent with the observed data under a specific task. In contrast, self-diffusion introduces a self-contained iterative process that alternates between noising and denoising steps to progressively refine its estimate of the solution. At each step of self-diffusion, noise is added to the current estimate, and a self-denoiser, which is a single untrained convolutional network randomly initialized from scratch, is continuously trained for certain iterations via a data fidelity loss to predict the solution from the noisy estimate. Essentially, self-diffusion exploits the spectral bias of neural networks and modulates it through a scheduled noise process. Without relying on pretrained score functions or external denoisers, this approach still remains adaptive to arbitrary forward operators and noisy observations, making it highly flexible and broadly applicable. We demonstrate the effectiveness of our approach on a variety of linear inverse problems, showing that self-diffusion achieves competitive or superior performance compared to other methods.

Deep Learning · Algorithms

Ruben Solozabal, Velibor Bojkovic, Hilal AlQuabeh, Kentaro Inui, Martin Takac

Current methods for initializing state space models (SSMs) parameters mainly rely on the \textit{HiPPO framework}, which is based on an online approximation of orthogonal polynomials. Recently, diagonal alternatives have shown to reach a similar level of performance while being significantly more efficient due to the simplification in the kernel computation. However, the \textit{HiPPO framework} does not explicitly study the role of its diagonal variants. In this paper, we take a further step to investigate the role of diagonal SSM initialization schemes from the frequency perspective. Our work seeks to systematically understand how to parameterize these models and uncover the learning biases inherent in such diagonal state-space models. Based on our observations, we propose a diagonal initialization on the discrete Fourier domain \textit{S4D-DFouT}. The insights in the role of pole placing in the initialization enable us to further scale them and achieve state-of-the-art results on the Long Range Arena benchmark, allowing us to train from scratch on very large datasets as PathX-256.

Probabilistic Methods · Gaussian Processes

Siavash Ameli, Chris van der Heide, Liam Hodgkinson, Michael Mahoney

Computing eigenvalues of very large matrices is a critical task in many machine learning applications, including the evaluation of log-determinants, the trace of matrix functions, and other important metrics. As datasets continue to grow in scale, the corresponding covariance and kernel matrices become increasingly large, often reaching magnitudes that make their direct formation impractical or impossible. Existing techniques typically rely on matrix-vector products, which can provide efficient approximations, if the matrix spectrum behaves well. However, in settings like distributed learning, or when the matrix is defined only indirectly, access to the full data set can be restricted to only very small sub-matrices of the original matrix. In these cases, the matrix of nominal interest is not even available as an implicit operator, meaning that even matrix-vector products may not be available. In such settings, the matrix is "impalpable", in the sense that we have access to only masked snapshots of it. We draw on principles from free probability theory to introduce a novel method of "free decompression" to estimate the spectrum of such matrices. Our method can be used to extrapolate from the empirical spectral densities of small submatrices to infer the eigenspectrum of extremely large (impalpable) matrices (that we cannot form or even evaluate with full matrix-vector products). We demonstrate the effectiveness of this approach through a series of examples, comparing its performance against known limiting distributions from random matrix theory in synthetic settings, as well as applying it to submatrices of real-world datasets, matching them with their full empirical eigenspectra.

Computer Vision · Vision Models & Multimodal

Tianhao Li, Tingfa Xu, Ying Wang, Haolin Qin, Xu Lin, Jianan Li

Drone-based multi-object tracking is essential yet highly challenging due to small targets, severe occlusions, and cluttered backgrounds. Existing RGB-based multi-object tracking algorithms heavily depend on spatial appearance cues such as color and texture, which often degrade in aerial views, compromising tracking reliability. Multispectral imagery, capturing pixel-level spectral reflectance, provides crucial spectral cues that significantly enhance object discriminability under degraded spatial conditions. However, the lack of dedicated multispectral UAV datasets has hindered progress in this domain. To bridge this gap, we introduce **MMOT**, the first challenging benchmark for drone-based multispectral multi-object tracking dataset. It features three key characteristics: (i) **Large Scale** — 125 video sequences with over 488.8K annotations across eight object categories; (ii) **Comprehensive Challenges** — covering diverse real-world challenges such as extreme small targets, high-density scenarios, severe occlusions and complex platform motion; and (iii) **Precise Oriented Annotations** — enabling accurate localization and reduced object ambiguity under aerial perspectives. To better extract spectral features and leverage oriented annotations, we further present a multispectral and orientation-aware MOT scheme adapting existing MOT methods, featuring: (i) a lightweight Spectral 3D-Stem integrating spectral features while preserving compatibility with RGB pretraining; (ii) a orientation-aware Kalman filter for precise state estimation; and (iii) an end-to-end orientation-adaptive transformer architecture. Extensive experiments across representative trackers consistently show that multispectral input markedly improves tracking performance over RGB baselines, particularly for small and densely packed objects. We believe our work will benefit the community for advancing drone-based multispectral multi-object tracking research. Our MMOT, code and benchmarks are publicly available at https://github.com/Annzstbl/MMOT.

Steffen Schotthöfer, Lexie Yang, Stefan Schnake

Deployment of neural networks on resource-constrained devices demands models that are both compact and robust to adversarial inputs. However, compression and adversarial robustness often conflict. In this work, we introduce a dynamical low-rank training scheme enhanced with a novel spectral regularizer that controls the condition number of the low-rank core in each layer. This approach mitigates the sensitivity of compressed models to adversarial perturbations without sacrificing clean accuracy. The method is model- and data-agnostic, computationally efficient, and supports rank adaptivity to automatically compress the network at hand. Extensive experiments across standard architectures, datasets, and adversarial attacks show the regularized networks can achieve over 94 compression while recovering or improving adversarial accuracy relative to uncompressed baselines.

Social Aspects · Accountability, Transparency and Interpretability

Ali Gorji, Andisheh Amrollahi, Andreas Krause

SHAP (SHapley Additive exPlanations) values are a widely used method for local feature attribution in interpretable and explainable AI. We propose an efficient two-stage algorithm for computing SHAP values in both black-box setting and tree-based models. Motivated by spectral bias in real-world predictors, we first approximate models using compact Fourier representations, exactly for trees and approximately for black-box models. In the second stage, we introduce a closed-form formula for {\em exactly} computing SHAP values using the Fourier representation, that ``linearizes'' the computation into a simple summation and is amenable to parallelization. As the Fourier approximation is computed only once, our method enables amortized SHAP value computation, achieving significant speedups over existing methods and a tunable trade-off between efficiency and precision.

Zhongnan Cai, Yingying Wang, Hui Zheng, Panwang Pan, Zixu Lin, Ge Meng, Chenxin Li, Chunming He, Jiaxin Xie, Yunlong Lin 等

Recently, deep learning-based pan-sharpening algorithms have achieved notable advancements over traditional methods. However, deep learning-based methods incur substantial computational overhead during inference, especially with large images. This excessive computational demand limits the applicability of these methods in real-world scenarios, particularly in the absence of dedicated computing devices such as GPUs and TPUs. To address these challenges, we propose Pan-LUT, a novel learnable look-up table (LUT) framework for pan-sharpening that strikes a balance between performance and computational efficiency for large remote sensing images. Our method makes it possible to process 15K$\times$15K remote sensing images on a 24GB GPU. To finely control the spectral transformation, we devise the PAN-guided look-up table (PGLUT) for channel-wise spectral mapping. To effectively capture fine-grained spatial details, we introduce the spatial details look-up table (SDLUT). Furthermore, to adaptively aggregate channel information for generating high-resolution multispectral images, we design an adaptive output look-up table (AOLUT). Our model contains fewer than 700K parameters and processes a 9K$\times$9K image in under 1 ms using one RTX 2080 Ti GPU, demonstrating significantly faster performance compared to other methods. Experiments reveal that Pan-LUT efficiently processes large remote sensing images in a lightweight manner, bridging the gap to real-world applications. Furthermore, our model surpasses SOTA methods in full-resolution scenes under real-world conditions, highlighting its effectiveness and efficiency.

Applications · Time Series

Jianyang Qin, Chaoyang Li, Jinhao Cui, Lingzhi Wang, Zhao Liu, Qing Liao

Recent studies reveal that Large Language Models (LLMs) exhibit strong sequential reasoning capabilities, allowing them to replace specialized time-series models and serve as foundation models for complex time-series analysis. To activate the capabilities of LLMs for time-series tasks, numerous studies have attempted to bridge the gap between time series and linguistics by aligning textual representations with time-series patterns. However, it is a non-trivial endeavor to losslessly capture the infinite time-domain variability using natural language, leading to suboptimal alignment performance. Beyond representation, contextual differences, where semantics in time series are conveyed by consecutive points, unlike in text by individual tokens, are often overlooked by existing methods. To address these, we propose S$^2$TS-LLM, a simple yet effective framework to repurpose LLMs for universal time series analysis through the following two main paradigms: (i) a spectral symbolization paradigm transforms time series into frequency-domain representations characterized by a fixed number of components and prominent amplitudes, which enables a limited set of symbols to effectively abstract key frequency features; (ii) a contextual segmentation paradigm partitions the sequence into blocks based on temporal patterns and reassigns positional encodings accordingly, thereby mitigating the structural mismatch between time series and natural language. Together, these paradigms bootstrap the LLMs' perception of temporal patterns and structures, effectively bridging time series and linguistics. Extensive experiments show that S$^2$TS-LLM can serve as a powerful time series analyzer, outperforming state-of-the-art methods across time series tasks.

Deep Learning · Graph Neural Networks

GUOGUO AI, Hezhe Qiao, Hui Yan, Guansong Pang

Current semi-supervised graph anomaly detection (GAD) methods utilizes a small set of labeled normal nodes to identify abnormal nodes from a large set of unlabeled nodes in a graph. These methods posit that 1) normal nodes share a similar level of homophily and 2) the labeled normal nodes can well represent the homophily patterns in the entire normal class. However, this assumption often does not hold well since normal nodes in a graph can exhibit diverse homophily in real-world GAD datasets. In this paper, we propose RHO, namely Robust Homophily Learning, to adaptively learn such homophily patterns. RHO consists of two novel modules, adaptive frequency response filters (AdaFreq) and graph normality alignment (GNA). AdaFreq learns a set of adaptive spectral filters that capture different frequency components of the labeled normal nodes with varying homophily in the channel-wise and cross-channel views of node attributes. GNA is introduced to enforce consistency between the channel-wise and cross-channel homophily representations to robustify the normality learned by the filters in the two views. Experiments on eight real-world GAD datasets show that RHO can effectively learn varying, often under-represented, homophily in the small labeled node set and substantially outperforms state-of-the-art competing methods. Code is available at \url{https://github.com/mala-lab/RHO}.

Deep Learning · Theory

Peter Ochieng

Contrastive learning thrives—or fails—based on how we construct \emph{positive} and \emph{negative} pairs. In the absence of explicit labels, models must infer semantic structure from these proxy signals. Early work on Siamese networks \citep{chopra2005learning,hadsell2006dimensionality} already showed that pair construction directly shapes learned representations. In modern contrastive frameworks, poor pair selection remains a primary failure mode: it either causes collapse, where all embeddings converge to a point, or wastes the representational capacity of the space \citep{chen2020simple,tian2020makes,khosla2020supervised}. Contemporary methods typically generate positives via semantic-preserving augmentations (crop, jitter, view transform), while negatives are drawn from other elements in the mini-batch under the assumption that different images are semantically dissimilar. But this assumption breaks down in fine-grained, low-diversity, or high-resolution settings \citep{kalantidis2020hard,robinson2020contrastive,chuang2020debiased}, motivating techniques such as hard-negative mining and debiased losses \citep{bachman2019learning,tian2020makes}. \paragraph{Beyond pairs: batch-level diversity.} While most prior work focuses on \emph{which} individual negatives to select, we study the geometry of the entire batch. Our central observation is this: the overall \emph{diversity} of the batch embedding space strongly governs both training dynamics and representational quality. If diversity is too low, the model sees nearly identical negatives and gradients vanish—leading to collapse. If diversity is too high, negatives become almost orthogonal, but the resulting gradients shrink in magnitude, and learning slows. Optimal training thus occurs within a \emph{moderate diversity window}: high enough to avoid collapse, low enough to preserve update strength.

Amitava Das, Suranjana Trivedy, Danush Khanna, Yaswanth Narsupalli, Basab Ghosh, Rajarshi Roy, Gurpreet Singh, Vinija Jain, Vasu Sharma, Aishwarya Naresh Reganti 等

The rapid advancement of large language models (LLMs) has revolutionized numerous applications, but presents significant challenges in aligning these models with diverse human values, ethical standards, and specific user preferences. Direct Preference Optimization (DPO) has become a cornerstone for preference alignment but is constrained by reliance on fixed divergence measures and limited feature transformations. We introduce DPO-Kernels, an innovative enhancement of DPO that integrates kernel methods to overcome these challenges through four key contributions: (i) Kernelized Representations: These representations enhance divergence measures by using polynomial, RBF, Mahalanobis, and spectral kernels for richer feature transformations. Additionally, we introduce a hybrid loss that combines embedding-based loss with probability-based loss; (ii) Divergence Alternatives: Beyond Kullback–Leibler (KL), we incorporate Jensen-Shannon, Hellinger, Rényi, Bhattacharyya, Wasserstein, and other f-divergences to boost stability and robustness; (iii) Data-Driven Selection: Choosing the optimal kernel-divergence pair among 28 combinations (4 kernels \times 7 divergences) is challenging. We introduce automatic metrics that analyze the data to select the best kernel-divergence pair, eliminating the need for manual tuning; (iv) Hierarchical Mixture of Kernels (HMK): Combining local and global kernels for precise and large-scale semantic modeling. This approach automatically selects the optimal kernel mixture during training, enhancing modeling flexibility. DPO-Kernels achieve state-of-the-art generalization in factuality, safety, reasoning, and instruction following across 12 datasets. While alignment risks overfitting, Heavy-Tailed Self-Regularization (HT-SR) theory confirms that DPO-Kernels ensure robust generalization in LLMs. Comprehensive resources are available to facilitate further research and application of DPO-Kernels.

General Machine Learning · Transfer, Multitask and Meta-learning

Filippo Rinaldi, Giacomo Capitani, Lorenzo Bonicelli, Donato Crisostomi, Federico Bolelli, ELISA FICARRA, Emanuele Rodola, Simone Calderara, Angelo Porrello

Foundation models serve as the backbone for numerous specialized models developed through fine-tuning. However, when the underlying pretrained model is updated or retrained (e.g., on larger and more curated datasets), the fine-tuned model becomes obsolete, losing its utility and requiring retraining. This raises the question: is it possible to transfer fine-tuning to a new release of the model? In this work, we investigate how to transfer fine-tuning to a new checkpoint without having to re-train, in a data-free manner. To do so, we draw principles from model re-basin and provide a recipe based on weight permutations to re-base the modifications made to the original base model, often called task vector. In particular, our approach tailors model re-basin for Transformer models, taking into account the challenges of residual connections and multi-head attention layers. Specifically, we propose a two-level method rooted in spectral theory, initially permuting the attention heads and subsequently adjusting parameters within select pairs of heads. Through extensive experiments on visual and textual tasks, we achieve the seamless transfer of fine-tuned knowledge to new pre-trained backbones without relying on a single training step or datapoint. Code is available at https://github.com/aimagelab/TransFusion.

Applications · Chemistry, Physics, and Earth Sciences

Xihang Yue, Yi Yang, Linchao Zhu

Recent advances in operator learning have produced two distinct approaches for solving partial differential equations (PDEs): attention-based methods offering point-level adaptability but lacking spectral constraints, and spectral-based methods providing domain-level continuity priors but limited in local flexibility. This dichotomy has hindered the development of PDE solvers with both strong flexibility and generalization capability. This work introduces Holistic Physics Mixer (HPM), a novel framework that bridges this gap by integrating spectral and physical information in a unified space. HPM unifies both approaches as special cases while enabling more powerful spectral-physical interactions beyond either method alone. This enables HPM to inherit both the strong generalization of spectral methods and the flexibility of attention mechanisms while avoiding their respective limitations. Through extensive experiments across diverse PDE problems, we demonstrate that HPM consistently outperforms state-of-the-art methods in both accuracy and computational efficiency, while maintaining strong generalization capabilities with limited training data and excellent zero-shot performance on unseen resolutions.

Applications · Computer Vision

Xingxing Yang, Jie Chen, Zaifeng Yang

This paper presents a novel approach to hyperspectral image (HSI) reconstruction from RGB images, addressing fundamental limitations in existing learning-based methods from a physical perspective. We discuss and aim to address the ``colorimetric dilemma": failure to consistently reproduce ground-truth RGB from predicted HSI, thereby compromising physical integrity and reliability in practical applications. To tackle this issue, we propose PhySpec, a physically consistent framework for robust HSI reconstruction. Our approach fundamentally exploits the intrinsic physical relationship between HSIs and corresponding RGBs by employing orthogonal subspace decomposition, which enables explicit estimation of camera spectral sensitivity (CSS). This ensures that our reconstructed spectra align with well-established physical principles, enhancing their reliability and fidelity. Moreover, to efficiently use internal information from test samples, we propose a self-supervised meta-auxiliary learning (MAXL) strategy that rapidly adapts the trained parameters to unseen samples using only a few gradient descent steps at test time, while simultaneously constraining the generated HSIs to accurately recover ground-truth RGB values. Thus, MAXL reinforces the physical integrity of the reconstruction process. Extensive qualitative and quantitative evaluations validate the efficacy of our proposed framework, showing superior performance compared to SOTA methods.

Deep Learning · Algorithms

Jialin Zhao, Yingtao Zhang, Xinghang Li, Huaping Liu, Carlo Cannistraci

The growing demands on GPU memory posed by the increasing number of neural network parameters call for training approaches that are more memory-efficient. Previous memory reduction training techniques, such as Low-Rank Adaptation (LoRA) and ReLoRA, face challenges, with LoRA being constrained by its low-rank structure, particularly during intensive tasks like pre-training, and ReLoRA suffering from saddle point issues. In this paper, we propose **S**parse **S**pectral **T**raining **(SST)** to optimize memory usage for **pre-training**. SST **updates all singular values** and **selectively updates singular vectors** through a multinomial sampling method weighted by the magnitude of the singular values. Furthermore, SST employs **singular value decomposition to initialize and periodically reinitialize** low-rank parameters, reducing distortion relative to full-rank training compared to other low-rank methods. Through comprehensive testing on both Euclidean and hyperbolic neural networks across various tasks, SST demonstrates its ability to outperform existing memory reduction training methods and is comparable to full-rank training in various cases. On LLaMA-1.3B, with only 18.7\% of the parameters trainable compared to full-rank training (using a rank equivalent to 6\% of the embedding dimension), SST reduces the perplexity gap between other low-rank methods and full-rank training by **97.4\%**. This result highlights SST as an effective parameter-efficient technique for model pre-training.

Deep Learning · Graph Neural Networks

Langzhang Liang, Fanchen Bu, Zixing Song, Zenglin Xu, Shirui Pan, Kijung Shin

The message-passing paradigm of Graph Neural Networks often struggles with exchanging information across distant nodes typically due to structural bottlenecks in certain graph regions, a limitation known as over-squashing. To reduce such bottlenecks, graph rewiring, which modifies graph topology, has been widely used. However, existing graph rewiring techniques often overlook the need to preserve critical properties of the original graph, e.g., spectral properties. Moreover, many approaches rely on increasing edge count to improve connectivity, which introduces significant computational overhead and exacerbates the risk of over-smoothing. In this paper, we propose a novel graph-rewiring method that leverages spectral graph sparsification for mitigating over-squashing. Specifically, our method generates graphs with enhanced connectivity while maintaining sparsity and largely preserving the original graph spectrum, effectively balancing structural bottleneck reduction and graph property preservation. Experimental results validate the effectiveness of our approach, demonstrating its superiority over strong baseline methods in classification accuracy and retention of the Laplacian spectrum.