论文检索

Deep Learning · Theory

Neil Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Misha Belkin

Neural networks trained to solve modular arithmetic tasks exhibit grokking, a phenomenon where the test accuracy starts improving long after the model achieves 100% training accuracy in the training process. It is often taken as an example of "emergence", where model ability manifests sharply through a phase transition. In this work, we show that the phenomenon of grokking is not specific to neural networks nor to gradient descent-based optimization. Specifically, we show that this phenomenon occurs when learning modular arithmetic with Recursive Feature Machines (RFM), an iterative algorithm that uses the Average Gradient Outer Product (AGOP) to enable task-specific feature learning with general machine learning models. When used in conjunction with kernel machines, iterating RFM results in a fast transition from random, near zero, test accuracy to perfect test accuracy. This transition cannot be predicted from the training loss, which is identically zero, nor from the test loss, which remains constant in initial iterations. Instead, as we show, the transition is completely determined by feature learning: RFM gradually learns block-circulant features to solve modular arithmetic. Paralleling the results for RFM, we show that neural networks that solve modular arithmetic also learn block-circulant features. Furthermore, we present theoretical evidence that RFM uses such block-circulant features to implement the Fourier Multiplication Algorithm, which prior work posited as the generalizing solution neural networks learn on these tasks. Our results demonstrate that emergence can result purely from learning task-relevant features and is not specific to neural architectures nor gradient descent-based optimization methods. Furthermore, our work provides more evidence for AGOP as a key mechanism for feature learning in neural networks.

General Machine Learning · Evaluation

Yilin Ye, Junchao Huang, Xingchen ZENG, Jiazhi Xia, Wei Zeng

Cross-modal embeddings form the foundation for multi-modal models. However, visualization methods for interpreting cross-modal embeddings have been primarily confined to traditional dimensionality reduction (DR) techniques like PCA and t-SNE. These DR methods primarily focus on feature distributions within a single modality, whilst failing to incorporate metrics (e.g., CLIPScore) across multiple modalities. This paper introduces AKRMap, a new DR technique designed to visualize cross-modal embeddings metric with enhanced accuracy by learning kernel regression of the metric landscape in the projection space. Specifically, AKRMap constructs a supervised projection network guided by a post-projection kernel regression loss, and employs adaptive generalized kernels that can be jointly optimized with the projection. This approach enables AKRMap to efficiently generate visualizations that capture complex metric distributions, while also supporting interactive features such as zoom and overlay for deeper exploration. Quantitative experiments demonstrate that AKRMap outperforms existing DR methods in generating more accurate and trustworthy visualizations. We further showcase the effectiveness of AKRMap in visualizing and comparing cross-modal embeddings for text-to-image models. Code and demo are available at https://github.com/yilinye/AKRMap.

Social Aspects · Security

Minh Vu, Geigh Zollicoffer, Huy Mai, Ben Nebgen, Boian S Alexandrov, Manish Bhattarai

Multimodal Machine Learning systems, particularly those aligning text and image data like CLIP/BLIP models, have become increasingly prevalent, yet remain susceptible to adversarial attacks. While substantial research has addressed adversarial robustness in unimodal contexts, defense strategies for multimodal systems are underexplored. This work investigates the topological signatures that arise between image and text embeddings and shows how adversarial attacks disrupt their alignment, introducing distinctive signatures. We specifically leverage persistent homology and introduce two novel Topological-Contrastive losses based on Total Persistence and Multi-scale kernel methods to analyze the topological signatures introduced by adversarial perturbations. We observe a pattern of monotonic changes in the proposed topological losses emerging in a wide range of attacks on image-text alignments, as more adversarial samples are introduced in the data. By designing an algorithm to back-propagate these signatures to input samples, we are able to integrate these signatures into Maximum Mean Discrepancy tests, creating a novel class of tests that leverage topological signatures for better adversarial detection.

Deep Learning · Generative Models and Autoencoders

Gianluigi Silvestri, Luca Ambrogioni, Chieh-Hsin Lai, Yuhta Takida, Yuki Mitsufuji

Consistency Training (CT) has recently emerged as a strong alternative to diffusion models for image generation. However, non-distillation CT often suffers from high variance and instability, motivating ongoing research into its training dynamics. We propose Variational Consistency Training (VCT), a flexible and effective framework compatible with various forward kernels, including those in flow matching. Its key innovation is a learned noise-data coupling scheme inspired by Variational Autoencoders, where a data-dependent encoder models noise emission. This enables VCT to adaptively learn noise-to-data pairings, reducing training variance relative to the fixed, unsorted pairings in classical CT. Experiments on multiple image datasets demonstrate significant improvements: our method surpasses baselines, achieves state-of-the-art FID among non-distillation CT approaches on CIFAR-10, and matches SoTA performance on ImageNet 64x64 with only two sampling steps. Code is available at https://github.com/sony/vct.

General Machine Learning · Causality

Kun Wang, Sumanth Varambally, Duncan Watson-Parris, Yian Ma, Rose Yu

Many important phenomena in scientific fields like climate, neuroscience, and epidemiology are naturally represented as spatiotemporal gridded data with complex interactions. Inferring causal relationships from these data is a challenging problem compounded by the high dimensionality of such data and the correlations between spatially proximate points. We present SPACY (SPAtiotemporal Causal discoverY), a novel framework based on variational inference, designed to model latent time series and their causal relationships from spatiotemporal data. SPACY alleviates the high-dimensional challenge by discovering causal structures in the latent space. To aggregate spatially proximate, correlated grid points, we use spatial factors, parametrized by spatial kernel functions, to map observational time series to latent representations. Theoretically, we generalize the problem to a continuous spatial domain and establish identifiability when the observations arise from a nonlinear, invertible function of the product of latent series and spatial factors. Using this approach, we avoid assumptions that are often unverifiable, including those about instantaneous effects or sufficient variability. Empirically, SPACY outperforms state-of-the-art baselines on synthetic data, even in challenging settings where existing methods struggle, while remaining scalable for large grids. SPACY also identifies key known phenomena from real-world climate data. An implementation of SPACY is available at \url{https://github.com/Rose-STL-Lab/SPACY/}

General Machine Learning · Hardware and Software

Zikai Zhou, Qizheng Zhang, Hermann Kumbong, Kunle Olukotun

Fine-tuning large language models (LLMs) is increasingly costly as models scale to hundreds of billions of parameters, and even parameter-efficient fine-tuning (PEFT) methods like LoRA remain resource-intensive.We introduce LowRA, the first framework to enable LoRA fine-tuning below 2 bits per parameter with minimal performance loss.LowRA optimizes fine-grained quantization—mapping, threshold selection, and precision assignment—while leveraging efficient CUDA kernels for scalable deployment.Extensive evaluations across 4 LLMs and 4 datasets show that LowRA achieves a superior performance–precision trade-off above 2 bits and remains accurate down to 1.15 bits, reducing memory usage by up to 50\%. Our results highlight the potential of ultra-low-bit LoRA fine-tuning for resource-constrained environments.

Theory · Learning Theory

Yingzhen Yang

We introduce a new tool, Transductive Local Complexity (TLC), to analyze the generalization performance of transductive learning methods and motivate new transductive learning algorithms. Our work extends the idea of the popular Local Rademacher Complexity (LRC) to the transductive setting with considerable and novel changes compared to the analysis of typical LRC methods in the inductive setting. While LRC has been widely used as a powerful tool in the analysis of inductive models with sharp generalization bounds for classification and minimax rates for nonparametric regression, it remains an open problem whether a localized version of Rademacher complexity based tool can be designed and applied to transductive learning and gain sharp bound for transductive learning which is consistent with the inductive excess risk bound by (LRC). We give a confirmative answer to this open problem by TLC. Similar to the development of LRC, we build TLC by first establishing a novel and sharp concentration inequality for supremum of empirical processes for the gap between test and training loss in the setting of sampling uniformly without replacement. Then a peeling strategy and a new surrogate variance operator are used to derive the following excess risk bound in the transductive setting, which is consistent with that of the classical LRC based excess risk bound in the inductive setting.As an application of TLC, we use the new TLC tool to analyze the Transductive Kernel Learning (TKL) model, and derive sharper excess risk bound than that by the current state-of-the-art. As a result of independent interest, the concentration inequality for the test-train process is used to derive a sharp concentration inequality for the general supremum of empirical process involving random variables in the setting of sampling uniformly without replacement, with comparison to current concentration inequalities.

Probabilistic Methods · Gaussian Processes

Jihao Andreas Lin, Sebastian Ament, Maximilian Balandat, David Eriksson, Jose Miguel Hernandez-Lobato, Eytan Bakshy

Applying Gaussian processes (GPs) to very large datasets remains a challenge due to limited computational scalability. Matrix structures, such as the Kronecker product, can accelerate operations significantly, but their application commonly entails approximations or unrealistic assumptions. In particular, the most common path to creating a Kronecker-structured kernel matrix is by evaluating a product kernel on gridded inputs that can be expressed as a Cartesian product. However, this structure is lost if any observation is missing, breaking the Cartesian product structure, which frequently occurs in real-world data such as time series. To address this limitation, we propose leveraging latent Kronecker structure, by expressing the kernel matrix of observed values as the projection of a latent Kronecker product. In combination with iterative linear system solvers and pathwise conditioning, our method facilitates inference of exact GPs while requiring substantially fewer computational resources than standard iterative methods. We demonstrate that our method outperforms state-of-the-art sparse and variational GPs on real-world datasets with up to five million examples, including robotics, automated machine learning, and climate applications.

General Machine Learning · Kernel methods

Zonghao Chen, Masha Naslidnyk, Francois-Xavier Briol

This paper considers the challenging computational task of estimating nested expectations. Existing algorithms, such as nested Monte Carlo or multilevel Monte Carlo, are known to be consistent but require a large number of samples at both inner and outer levels to converge. Instead, we propose a novel estimator consisting of nested kernel quadrature estimators and we prove that it has a faster convergence rate than all baseline methods when the integrands have sufficient smoothness. We then demonstrate empirically that our proposed method does indeed require the fewest number of samples to estimate nested expectations over a range of real-world application areas from Bayesian optimisation to option pricing and health economics.

Probabilistic Methods · Monte Carlo and Sampling Methods

Tiange Liu, Nikola Surjanovic, Miguel Biron-Lattes, Alexandre Bouchard-Côté, Trevor Campbell

Many common Markov chain Monte Carlo (MCMC) kernels can be formulated using a deterministic involutive proposal with a step size parameter. Selecting an appropriate step size is often a challenging task in practice; and for complex multiscale targets, there may not be one choice of step size that works well globally. In this work, we address this problem with a novel class of involutive MCMC methods---AutoStep MCMC---that selects an appropriate step size at each iteration adapted to the local geometry of the target distribution. Weprove that under mild conditions AutoStep MCMC is $\pi$-invariant, irreducible, and aperiodic, and obtain bounds on expected energy jump distance and cost per iteration. Empirical results examine the robustness and efficacy of our proposed step size selection procedure, and show that AutoStep MCMC is competitive with state-of-the-art methods in terms of effective sample size per unit cost on a range of challenging target distributions.

Deep Learning · Algorithms

Andrei Panferov, Jiale Chen, Rush Tabesh, Mahdi Nikdan, Dan Alistarh

One approach to reducing the massive costs of large language models (LLMs) is the use of quantized or sparse representations for training or deployment.While post-training compression methods are very popular, the question of obtaining even more accurate compressed models by *directly training* over such representations, i.e., *Quantization-Aware Training (QAT)*, is still open: for example, a recent study put the "optimal" bit-width at which models can be trained using QAT, while staying accuracy-competitive with standard FP16/BF16 precision, at 8-bits weights and activations. We advance this state-of-the-art via a new method called QuEST, for which we demonstrate optimality at 4-bits and stable convergence as low as 1-bit weights and activations. QuEST achieves this by improving two key aspects of QAT methods: (1) accurate and fast quantization of the (continuous) distributions of weights and activations via Hadamard normalization and MSE-optimal fitting; (2) a new *trust gradient estimator* based on the idea of explicitly minimizing the error between the noisy gradient computed over quantized states and the "true" (but unknown) full-precision gradient. Experiments on Llama-type architectures show that QuEST induces stable scaling laws across the entire range of hardware-supported precisions, and can be extended to sparse representations. We provide GPU kernel support showing that models produced by QuEST can be executed efficiently. Our code is available at [https://github.com/IST-DASLab/QuEST](https://github.com/IST-DASLab/QuEST).

Optimization

Yu Wang, Mazdak Abulnaga, Yaël Balbastre, Bruce Fischl

Sparse linear solvers are fundamental to science and engineering, applied in partial differential equations (PDEs), scientific computing, computer vision, and beyond. Indirect solvers possess characteristics that make them undesirable as stable differentiable modules; existing direct solvers, though reliable, are too expensive to be adopted in neural architectures. We substantially accelerate direct sparse solvers or generalized deconvolution by up to 3 orders-of-magnitude faster, violating common assumptions that direct solvers are too slow. We ``condense'' a sparse Laplacian matrix into a dense tensor, a compact data structure that batch-wise stores the Dirichlet-to-Neumann matrices, reducing the sparse solving to recursively merging pairs of dense matrices that are much smaller. The batched small dense systems are sliced and inverted in parallel to take advantage of dense GPU BLAS kernels, highly optimized in the era of deep learning. Our method is efficient, qualified as a strong zero-shot baseline for AI-based PDE solving and a reliable differentiable module integrable into machine learning pipelines.

Deep Learning · Algorithms

Antoine Gonon, Léon Zheng, Pascal Carrivain, TUNG LE

Kronecker-sparse (KS) matrices—whose supports are Kronecker products of identity and all-ones blocks—underpin the structure of Butterfly and Monarch matrices and offer the promise of more efficient models. However, existing GPU kernels for KS matrix multiplication suffer from high data movement costs, with up to 50% of time spent on memory-bound tensor permutations. We propose a fused, output-stationary GPU kernel that eliminates these overheads, reducing global memory traffic threefold. Across 600 KS patterns, our kernel achieves in FP32 a median speedup of x1.4 and lowers energy consumption by 15%. A simple heuristic based on KS pattern parameters predicts when our method outperforms existing ones. We release all code at [github.com/PascalCarrivain/ksmm](https://github.com/PascalCarrivain/ksmm), including a PyTorch-compatible *KSLinear* layer, and demonstrate in FP32 end-to-end latency reductions of up to 22% in ViT-S/16 and 16% in GPT-2 medium.

Probabilistic Methods · Gaussian Processes

Sidhanth Holalkere, David S Bindel, Silvia Sellán, Alexander Terenin

Poisson Surface Reconstruction is a widely-used algorithm for reconstructing a surface from an oriented point cloud. To facilitate applications where only partial surface information is available, or scanning is performed sequentially, a recent line of work proposes to incorporate uncertainty into the reconstructed surface via Gaussian process models. The resulting algorithms first perform Gaussian process interpolation, then solve a set of volumetric partial differential equations globally in space, resulting in a computationally expensive two-stage procedure. In this work, we apply recently-developed techniques from geometric Gaussian processes to combine interpolation and surface reconstruction into a single stage, requiring only one linear solve per sample. The resulting reconstructed surface samples can be queried locally in space, without the use of problem-dependent volumetric meshes or grids. These capabilities enable one to (a) perform probabilistic collision detection locally around the region of interest, (b) perform ray casting without evaluating points not on the ray's trajectory, and (c) perform next-view planning on a per-ray basis. They also do not requiring one to approximate kernel matrix inverses with diagonal matrices as part of intermediate computations, unlike prior methods. Results show that our approach provides a cleaner, more-principled, and more-flexible stochastic surface reconstruction pipeline.

Probabilistic Methods · Bayesian Models and Methods

Ruth Wan Theng Chew, Quoc Phong Nguyen, Bryan Kian Hsiang Low

Bilevel optimization is characterized by a two-level optimization structure, where the upper-level problem is constrained by optimal lower-level solutions, and such structures are prevalent in real-world problems. The constraint by optimal lower-level solutions poses significant challenges, especially in noisy, constrained, and derivative-free settings, as repeating lower-level optimizations is sample inefficient and predicted lower-level solutions may be suboptimal. We present BILevel Bayesian Optimization (BILBO), a novel Bayesian optimization algorithm for general bilevel problems with blackbox functions, which optimizes both upper- and lower-level problems simultaneously, without the repeated lower-level optimization required by existing methods. BILBO samples from confidence-bounds based trusted sets, which bounds the suboptimality on the lower level. Moreover, BILBO selects only one function query per iteration, where the function query selection strategy incorporates the uncertainty of estimated lower-level solutions and includes a conditional reassignment of the query to encourage exploration of the lower-level objective. The performance of BILBO is theoretically guaranteed with a sublinear regret bound for commonly used kernels and is empirically evaluated on several synthetic and real-world problems.

Applications · Chemistry, Physics, and Earth Sciences

Yiming Yang, Xiaoyuan Cheng, Daniel Giles, Sibo Cheng, Yi He, Xiao Xue, Boli Chen, Yukun Hu

Variational data assimilation estimates the dynamical system states by minimizing a cost function that fits the numerical models with the observational data. Although four-dimensional variational assimilation (4D-Var) is widely used, it faces high computational costs in complex nonlinear systems and depends on imperfect state-observation mappings. Deep learning (DL) offers more expressive approximators, while integrating DL models into 4D-Var is challenging due to their nonlinearities and lack of theoretical guarantees in assimilation results. In this paper, we propose \textit{Tensor-Var}, a novel framework that integrates kernel conditional mean embedding (CME) with 4D-Var to linearize nonlinear dynamics, achieving convex optimization in a learned feature space. Moreover, our method provides a new perspective for solving 4D-Var in a linear way, offering theoretical guarantees of consistent assimilation results between the original and feature spaces. To handle large-scale problems, we propose a method to learn deep features (DFs) using neural networks within the Tensor-Var framework. Experiments on chaotic systems and global weather prediction with real-time observations show that Tensor-Var outperforms conventional and DL hybrid 4D-Var baselines in accuracy while achieving a 10- to 20-fold speed improvement.

General Machine Learning · Kernel methods

Ashkan Soleymani, Behrooz Tahmasebi, Stefanie Jegelka, Patrick Jaillet

We study the statistical-computational trade-offs for learning with exact invariances (or symmetries) using kernel regression. Traditional methods, such as data augmentation, group averaging, canonicalization, and frame-averaging, either fail to provide a polynomial-time solution or are not applicable in the kernel setting. However, with oracle access to the geometric properties of the input space, we propose a polynomial-time algorithm that learns a classifier with \emph{exact} invariances. Moreover, our approach achieves the same excess population risk (or generalization error) as the original kernel regression problem. To the best of our knowledge, this is the first polynomial-time algorithm to achieve exact (as opposed to approximate) invariances in this setting, partially addressing a question posed by Diaz (2025) regarding the avoidance of prohibitively large and computationally intensive group averaging methods in kernel regression with exact invariances. Our proof leverages tools from differential geometry, spectral theory, and optimization. A key result in our development is a new reformulation of the problem of learning under invariances as optimizing an infinite number of linearly constrained convex quadratic programs, which may be of independent interest.

General Machine Learning · Unsupervised and Semi-supervised Learning

Walid Durani, Tobias Nitzl, Claudia Plant, Christian Böhm

Detecting anomalies with limited supervision is challenging due to the scarcity of labeled anomalies, which often fail to capture the diversity of abnormal behaviors. We propose Weakly Supervised Anomaly Detection via Dual-Tailed Kernel (WSAD-DT), a novel framework that learns robust latent representations to distinctly separate anomalies from normal samples under weak supervision. WSAD-DT introduces two centroids—one for normal samples and one for anomalies—and leverages a dual-tailed kernel scheme: a light-tailed kernel to compactly model in-class points and a heavy-tailed kernel to main- tain a wider margin against out-of-class instances. To preserve intra-class diversity, WSAD-DT in- corporates kernel-based regularization, encouraging richer representations within each class. Furthermore, we devise an ensemble strategy that partition unlabeled data into diverse subsets, while sharing the limited labeled anomalies among these partitions to maximize their impact. Empirically, WSAD-DT achieves state-of-the-art performance on several challenging anomaly detection benchmarks, outperforming leading ensemble-based methods such as XGBOD.

General Machine Learning · Causality

Yiqing Li, Yewei Xia, Xiaofei Wang, Zhengming Chen, Liuhua Peng, Mingming Gong, Kun Zhang

Discovering dependence patterns between variables from observational data is a fundamental issue in data analysis. However, existing testing methods often fail to detect subtle yet critical patterns that occur within small regions of the data distribution--patterns we term rare dependence. These rare dependencies obscure the true underlying dependence structure in variables, particularly in causal discovery tasks. To address this issue, we propose a novel testing method that combines kernel-based (conditional) independence testing with adaptive sample importance reweighting. By learning and assigning higher importance weights to data points exhibiting significant dependence, our method amplifies the patterns and can detect them successfully. Theoretically, we analyze the asymptotic distributions of the statistics in this method and show the uniform bound of the learning scheme. Furthermore, we integrate our tests into the PC algorithm, a constraint-based approach for causal discovery, equipping it to uncover causal relationships even in the presence of rare dependence. Empirical evaluation of synthetic and real-world datasets comprehensively demonstrates the efficacy of our method.

Deep Learning · Graph Neural Networks

Masahiro Negishi, Thomas Gärtner, Pascal Welke

We investigate the distance function learned by message passing neural networks (MPNNs) in specific tasks, aiming to capture the _functional_ distance between prediction targets that MPNNs implicitly learn. This contrasts with previous work, which links MPNN distances on arbitrary tasks to _structural_ distances on graphs that ignore task-specific information. To address this gap, we distill the distance between MPNN embeddings into an interpretable graph distance. Our method uses optimal transport on the Weisfeiler Leman Labeling Tree (WILT), where the edge weights reveal subgraphs that strongly influence the distance between embeddings. This approach generalizes two well-known graph kernels and can be computed in linear time. Through extensive experiments, we demonstrate that MPNNs define the relative position of embeddings by focusing on a small set of subgraphs that are known to be functionally important in the domain.