论文检索

Yun Zhang, Xue Geng, Lizi Liao, Jintong Sun, Minghe Yu, Ge Yu

Quantizing large language models (LLMs) is essential for reducing memory and computational costs in natural language processing. Existing methods combine quantization with parameter-efficient fine-tuning but often fail to meet practical performance requirements. This paper introduces MeMoTune, a novel fine-tuning framework for quantized LLMs. By employing a measure and moment approach within a low-rank approximation framework in probability measure space, MeMoTune optimizes the objective function for superior fine-tuning results. The update process is further refined through scaled gradient, enhancing convergence efficiency and noise robustness. Experiments on tasks like text generation, summarization, and understanding show MeMoTune significantly outperforms state-of-the-art methods, e.g. fine-tuning Llama2-13B on GSM8K improves accuracy by 5.5%, while fine-tuning DeBERTaV3-base on CoLA of GLUE increases Matthews correlation by 1.7%. The code is publicly available at: https://github.com/hddyyyb/MeMoTune.

Taywon Min, Haeone Lee, Yongchan Kwon, Kimin Lee

In Reinforcement Learning from Human Feedback (RLHF), it is crucial to learn suitable reward models from human feedback to align large language models (LLMs) with human intentions. However, human feedback can often be noisy, inconsistent, or biased, especially when evaluating complex responses. Such feedback can lead to misaligned reward signals, potentially causing unintended side effects during the RLHF process. To address these challenges, we explore the use of influence functions to measure the impact of human feedback on the performance of reward models. We propose a compute-efficient approximation method that enables the application of influence functions to LLM-based reward models and large-scale preference datasets. Our experiments showcase two key applications of influence functions: (1) detecting common labeler biases in human feedback datasets and (2) guiding labelers in refining their strategies to better align with expert feedback. By quantifying the impact of human feedback, we believe that influence functions can enhance feedback interpretability and contribute to scalable oversight in RLHF, helping labelers provide more accurate and consistent feedback. Source code is available at https://github.com/mintaywon/IF_RLHF.

Dongjin Park, Eunsang Lee, Joon-Woo Lee

We propose Powerformer, an efficient homomorphic encryption (HE)-based privacy-preserving language model (PPLM) designed to reduce computation overhead while maintaining model performance. Powerformer incorporates three key techniques to optimize encrypted computations:1. A novel distillation technique that replaces softmax and layer normalization (LN) with computationally efficient power and linear functions, ensuring no performance degradation while enabling seamless encrypted computation.2. A pseudo-sign composite approximation method that accurately approximates GELU and tanh functions with minimal computational overhead.3. A homomorphic matrix multiplication algorithm specifically optimized for Transformer models, enhancing efficiency in encrypted environments.By integrating these techniques, Powerformer based on the BERT-base model achieves a 45% reduction in computation time compared to the state-of-the-art HE-based PPLM without any loss in accuracy.

Reinforcement Learning

Jumman Hossain, Nirmalya Roy

Reinforcement learning (RL) in real-world tasks such as robotic navigation often encounters environments with asymmetric traversal costs, where actions like climbing uphill versus moving downhill incur distinctly different penalties, or transitions may become irreversible. While recent quasimetric RL methods relax symmetry assumptions, they typically do not explicitly account for path-dependent costs or provide rigorous safety guarantees. We introduce Quasi-Potential Reinforcement Learning (QPRL), a novel framework that explicitly decomposes asymmetric traversal costs into a path-independent potential function ($\Phi$) and a path-dependent residual ($\Psi$). This decomposition allows efficient learning and stable policy optimization via a Lyapunov-based safety mechanism. Theoretically, we prove that QPRL achieves convergence with improved sample complexity of $\tilde{O}(\sqrt{T})$, surpassing prior quasimetric RL bounds of $\tilde{O}(T)$. Empirically, our experiments demonstrate that QPRL attains state-of-the-art performance across various navigation and control tasks, significantly reducing irreversible constraint violations by approximately $4\times$ compared to baselines.

Applications · Chemistry, Physics, and Earth Sciences

Jiachen Guo, Xiaoyu Xie, Chanwook Park, Hantao Zhang, Matthew Politis, Gino Domel, Jiachen Guo

Deep learning has been extensively employed as a powerful function approximator for modeling physics-based problems described by partial differential equations (PDEs). Despite their popularity, standard deep learning models often demand prohibitively large computational resources and yield limited accuracy when scaling to large-scale, high-dimensional physical problems. Their black-box nature further hinders their application in industrial problems where interpretability and high precision are critical. To overcome these challenges, this paper introduces Interpolating Neural Network-Tensor Decomposition (INN-TD), a scalable and interpretable framework that has the merits of both machine learning and finite element methods for modeling large-scale physical systems. By integrating locally supported interpolation functions from finite element into the network architecture, INN-TD achieves a sparse learning structure with enhanced accuracy, faster training/solving speed, and reduced memory footprint. This makes it particularly effective for tackling large-scale high-dimensional parametric PDEs in training, solving, and inverse optimization tasks in physical problems where high precision is required.

Social Aspects · Alignment

Ariel Procaccia, Benjamin Schiffer, Shirley Zhang

A key challenge in training Large Language Models (LLMs) is properly aligning them with human preferences. Reinforcement Learning with Human Feedback (RLHF) uses pairwise comparisons from human annotators to train reward functions and has emerged as a popular alignment method. However, input datasets in RLHF can be unbalanced due to adversarial manipulation or inadvertent repetition. Therefore, we want RLHF algorithms to perform well even when the set of alternatives is not uniformly distributed. Drawing on insights from social choice theory, we introduce robustness to approximate clones, a desirable property of RLHF algorithms which requires that adding near-duplicate alternatives does not significantly change the learned reward function. We first demonstrate that the standard RLHF algorithm based on regularized maximum likelihood estimation (MLE) fails to satisfy this property. We then propose the weighted MLE, a new RLHF algorithm that modifies the standard regularized MLE by weighting alternatives based on their similarity to other alternatives. This new algorithm guarantees robustness to approximate clones while preserving desirable theoretical properties.

Theory · Learning Theory

Amirhossein Roknilamouki, Arnob Ghosh, Ming Shi, Fatemeh Nourzad, Eylem Ekici, Ness Shroff

In Reinforcement Learning (RL), tasks with instantaneous hard constraints present significant challenges, particularly when the decision space is non-convex or non-star-convex. This issue is especially relevant in domains like autonomous vehicles and robotics, where constraints such as collision avoidance often take a non-convex form. In this paper, we establish a regret bound of $\tilde{\mathcal{O}}((1 + \tfrac{1}{\tau}) \sqrt{\log(\frac{1}{\tau}) d^3 H^4 K})$, applicable to both star-convex and non-star-convex cases, where $d$ is the feature dimension, $H$ the episode length, $K$ the number of episodes, and $\tau$ the safety threshold. Moreover, the violation of safety constraints is zero with high probability throughout the learning process. A key technical challenge in these settings is bounding the covering number of the value-function class, which is essential for achieving value-aware uniform concentration in model-free function approximation. For the star-convex setting, we develop a novel technique called *Objective–Constraint Decomposition* (OCD) to properly bound the covering number. This result also resolves an error in a previous work on constrained RL. In non-star-convex scenarios, where the covering number can become infinitely large, we propose a two-phase algorithm, Non-Convex Safe Least Squares Value Iteration (NCS-LSVI), which first reduces uncertainty about the safe set by playing a known safe policy. After that, it carefully balances exploration and exploitation to achieve the regret bound. Finally, numerical simulations on an autonomous driving scenario demonstrate the effectiveness of NCS-LSVI.

Probabilistic Methods

Charita Dellaporta, Patrick O'Hara, Theodoros Damoulas

Decision making under uncertainty is challenging as the data-generating process (DGP) is often unknown. Bayesian inference proceeds by estimating the DGP through posterior beliefs on the model’s parameters. However, minimising the expected risk under these beliefs can lead to suboptimal decisions due to model uncertainty or limited, noisy observations. To address this, we introduce Distributionally Robust Optimisation with Bayesian Ambiguity Sets (DRO-BAS) which hedges against model uncertainty by optimising the worst-case risk over a posterior-informed ambiguity set. We provide two such sets, based on the posterior expectation (DRO-BAS(PE)) or the posterior predictive (DRO-BAS(PP)) and prove that both admit, under conditions, strong dual formulations leading to efficient single-stage stochastic programs which are solved with a sample average approximation. For DRO-BAS(PE), this covers all conjugate exponential family members while for DRO-BAS(PP) this is shown under conditions on the predictive's moment generating function. Our DRO-BAS formulations outperform existing Bayesian DRO on the Newsvendor problem and achieve faster solve times with comparable robustness on the Portfolio problem.

Theory · Reinforcement Learning and Planning

Joongkyu Lee, Min-hwan Oh

In this paper, we consider combinatorial reinforcement learning with preference feedback, where a learning agent sequentially offers an action—an assortment of multiple items—to a user, whose preference feedback follows a multinomial logistic (MNL) model. This framework allows us to model real-world scenarios, particularly those involving long-term user engagement, such as in recommender systems and online advertising. However, this framework faces two main challenges: (1) the unknown value of each item, unlike traditional MNL bandits that only address single-step preference feedback, and (2) the difficulty of ensuring optimism while maintaining tractable assortment selection in the combinatorial action space with unknown values. In this paper, we assume a contextual MNL preference model, where the mean utilities are linear, and the value of each item is approximated by a general function. We propose an algorithm, MNL-VQL, that addresses these challenges, making it both computationally and statistically efficient. As a special case, for linear MDPs (with the MNL preference feedback), we establish the first regret lower bound in this framework and show that MNL-VQL achieves near-optimal regret. To the best of our knowledge, this is the first work to provide statistical guarantees in combinatorial RL with preference feedback.

Optimization · Everything Else

Shiyu Wang, Mariam Avagyan, Yihan Shen, Arnaud Lamy, Tingran Wang, Szabolcs Marka, Zsuzsanna Marka, John Wright

Learned denoisers play a fundamental role in various signal generation (e.g., diffusion models) and reconstruction (e.g., compressed sensing) architectures, whose success derives from their ability to leverage low-dimensional structure in data. Existing denoising methods, however, either rely on local approximations that require a linear scan of the entire dataset or treat denoising as generic function approximation problems, sacrificing efficiency and interpretability. We consider the problem of efficiently denoising a new noisy data point sampled from an unknown manifold $\mathcal M \in \mathbb{R}^D$, using only noisy samples. This work proposes a framework for test-time efficient manifold denoising, by framing the concept of "learning-to-denoise" as *"learning-to-optimize"*. We have two technical innovations: (i) *online learning* methods which learn to optimize over the manifold of clean signals using only noisy data, effectively "growing" an optimizer one sample at a time. (ii) *mixed-order* methods which guarantee that the learned optimizers achieve global optimality, ensuring both efficiency and near-optimal denoising performance. We corroborate these claims with theoretical analyses of both the complexity and denoising performance of mixed-order traversal. Our experiments on scientific manifolds demonstrate significantly improved complexity-performance tradeoffs compared to nearest neighbor search, which underpins existing provable denoising approaches based on exhaustive search.

General Machine Learning · Online Learning, Active Learning and Bandits

Yegon Kim, Hyunsu Kim, Gyeonghoon Ko, Juho Lee

Accurately solving partial differential equations (PDEs) is critical to understanding complex scientific and engineering phenomena, yet traditional numerical solvers are computationally expensive. Surrogate models offer a more efficient alternative, but their development is hindered by the cost of generating sufficient training data from numerical solvers. In this paper, we present a novel framework for active learning (AL) in PDE surrogate modeling that reduces this cost. Unlike the existing AL methods for PDEs that always acquire entire PDE trajectories, our approach strategically generates only the most important time steps with the numerical solver, while employing the surrogate model to approximate the remaining steps. This dramatically reduces the cost incurred by each trajectory and thus allows the active learning algorithm to try out a more diverse set of trajectories given the same budget. To accommodate this novel framework, we develop an acquisition function that estimates the utility of a set of time steps by approximating its resulting variance reduction. We demonstrate the effectiveness of our method on several benchmark PDEs, including the Burgers' equation, Korteweg–De Vries equation, Kuramoto–Sivashinsky equation, the incompressible Navier-Stokes equation, and the compressible Navier-Stokes equation.Experiments show that our approach improves performance by large margins over the best existing method. Our method not only reduces average error but also the 99\%, 95\%, and 50\% quantiles of error, which is rare for an AL algorithm. All in all, our approach offers a data-efficient solution to surrogate modeling for PDEs.

Theory · Learning Theory

Thanh Nguyen-Tang, Raman Arora

We study policy-regret minimization problem in dynamically evolving environments, modeled as Markov games between a learner and a strategic, adaptive opponent. We propose a general algorithmic framework that achieves the optimal $\mathcal{O}(\sqrt{T})$ policy regret for a wide class of large-scale problems characterized by an Eluder-type condition--extending beyond the tabular settings of previous work. Importantly, our framework uncovers a simpler yet powerful algorithmic approach for handling reactive adversaries, demonstrating that leveraging opponent learning in such settings is key to attaining the optimal $\mathcal{O}(\sqrt{T})$ policy regret.

General Machine Learning · Everything Else

Zihan Zhou, Yang Zhou, Zijie Zhang, Lingjuan Lyu, Da Yan, Ruoming Jin, Dejing Dou

Machine unlearning (MU) aims to remove the influence of specific data points from trained models, enhancing compliance with privacy regulations. However, the vulnerability of basic MU models to malicious unlearning requests in adversarial learning environments has been largely overlooked. Existing adversarial MU attacks suffer from three key limitations: inflexibility due to pre-defined attack targets, inefficiency in handling multiple attack requests, and instability caused by non-convex loss functions. To address these challenges, we propose a Flexible, Efficient, and Stable Attack (DDPA). First, leveraging Carathéodory's theorem, we introduce a convex polyhedral approximation to identify points in the loss landscape where convexity approximately holds, ensuring stable attack performance. Second, inspired by simplex theory and John's theorem, we develop a regular simplex detection technique that maximizes coverage over the parameter space, improving attack flexibility and efficiency. We theoretically derive the proportion of the effective parameter space occupied by the constructed simplex. We evaluate the attack success rate of our DDPA method on real datasets against state-of-the-art machine unlearning attack methods. Our source code is available at https://github.com/zzz0134/DDPA.

Theory · Deep Learning

Duc Anh Nguyen, Ernesto Araya, Adalbert Fono, Gitta Kutyniok

Recent years have seen significant progress in developing spiking neural networks (SNNs) as a potential solution to the energy challenges posed by conventional artificial neural networks (ANNs). However, our theoretical understanding of SNNs remains relatively limited compared to the ever-growing body of literature on ANNs. In this paper, we study a discrete-time model of SNNs based on leaky integrate-and-fire (LIF) neurons, referred to as discrete-time LIF-SNNs, a widely used framework that still lacks solid theoretical foundations. We demonstrate that discrete-time LIF-SNNs realize piecewise constant functions defined on polyhedral regions, and more importantly, we quantify the network size required to approximate continuous functions. Moreover, we investigate the impact of latency (number of time steps) and depth (number of layers) on the complexity of the input space partitioning induced by discrete-time LIF-SNNs. Our analysis highlights the importance of latency and contrasts these networks with ANNs that use piecewise linear activation functions. Finally, we present numerical experiments to support our theoretical findings.

Theory · Learning Theory

Zimeng Li, Hongjun LI, Jingyuan Wang, Ke Tang

While deep learning has witnessed remarkable achievements in a wide range of applications, its substantial computational cost imposes limitations on application scenarios of neural networks. To alleviate this problem, low-rank compression is proposed as a class of efficient and hardware-friendly network compression methods, which reduce computation by replacing large matrices in neural networks with products of two small ones. In this paper, we implement low-rank networks by inserting a sufficiently narrow linear layer without bias between each of two adjacent nonlinear layers. We prove that low-rank Swish networks with a fixed depth are capable of approximating any function from the Hölder ball $\mathcal{C}^{\beta, R}([0,1]^d)$ within an arbitrarily small error where $\beta$ is the smooth parameter and $R$ is the radius. Our proposed constructive approximation ensures that the width of linear hidden layers required for approximation is no more than one-third of the width of nonlinear layers, which implies that the computational cost can be decreased by at least one-third compared with a network with the same depth and width of nonlinear layers but without narrow linear hidden layers. Our theoretical finding can offer a theoretical basis for low-rank compression from the perspective of universal approximation theory.

Social Aspects · Accountability, Transparency, and Interpretability

Amr Alkhatib, Roman Bresson, Henrik Boström, Michalis Vazirgiannis

Shapley values have several desirable, theoretically well-supported, properties for explaining black-box model predictions. Traditionally, Shapley values are computed post-hoc, leading to additional computational cost at inference time. To overcome this, a novel method, called ViaSHAP, is proposed, that learns a function to compute Shapley values, from which the predictions can be derived directly by summation. Two approaches to implement the proposed method are explored; one based on the universal approximation theorem and the other on the Kolmogorov-Arnold representation theorem. Results from a large-scale empirical investigation are presented, showing that ViaSHAP using Kolmogorov-Arnold Networks performs on par with state-of-the-art algorithms for tabular data. It is also shown that the explanations of ViaSHAP are significantly more accurate than the popular approximator FastSHAP on both tabular data and images.

Applications · Health / Medicine

Qingtian Zhu, Yumin Zheng, Yuling Sang, Yifan Zhan, Ziyan Zhu, Jun Ding, Yinqiang Zheng

Spatial Transcriptomics (ST) is a method that captures gene expression profiles aligned with spatial coordinates. The discrete spatial distribution and the super-high dimensional sequencing results make ST data challenging to be modeled effectively. In this paper, we manage to model ST in a continuous and compact manner by the proposed tool, SUICA, empowered by the great approximation capability of Implicit Neural Representations (INRs) that can enhance both the spatial density and the gene expression. Concretely within the proposed SUICA, we incorporate a graph-augmented Autoencoder to effectively model the context information of the unstructured spots and provide informative embeddings that are structure-aware for spatial mapping. We also tackle the extremely skewed distribution in a regression-by-classification fashion and enforce classification-based loss functions for the optimization of SUICA. By extensive experiments of a wide range of common ST platforms under varying degradations, SUICA outperforms both conventional INR variants and SOTA methods regarding numerical fidelity, statistical correlation, and bio-conservation. The prediction by SUICA also showcases amplified gene signatures that enriches the bio-conservation of the raw data and benefits subsequent analysis.

Deep Learning · Generative Models and Autoencoders

Xinyu Peng, Ziyang Zheng, Yaoming Wang, Han Li, Nuowen Kan, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong

We propose Noise Conditional Variational Score Distillation (NCVSD), a novel method for distilling pretrained diffusion models into generative denoisers. We achieve this by revealing that the unconditional score function implicitly characterizes the score function of denoising posterior distributions. By integrating this insight into the Variational Score Distillation (VSD) framework, we enable scalable learning of generative denoisers capable of approximating samples from the denoising posterior distribution across a wide range of noise levels. The proposed generative denoisers exhibit desirable properties that allow fast generation while preserve the benefit of iterative refinement: (1) fast one-step generation through sampling from pure Gaussian noise at high noise levels; (2) improved sample quality by scaling the test-time compute with multi-step sampling; and (3) zero-shot probabilistic inference for flexible and controllable sampling. We evaluate NCVSD through extensive experiments, including class-conditional image generation and inverse problem solving. By scaling the test-time compute, our method outperforms teacher diffusion models and is on par with consistency models of larger sizes. Additionally, with significantly fewer NFEs than diffusion-based methods, we achieve record-breaking LPIPS on inverse problems.

Applications · Robotics

Manan Tayal, Aditya Singh, Shishir Nadubettu Yadukumar, Somil Bansal

As autonomous systems become more ubiquitous in daily life, ensuring high performance with guaranteed safety is crucial. However, safety and performance could be competing objectives, which makes their co-optimization difficult. Learning-based methods, such as Constrained Reinforcement Learning (CRL), achieve strong performance but lack formal safety guarantees due to safety being enforced as soft constraints, limiting their use in safety-critical settings. Conversely, formal methods such as Hamilton-Jacobi (HJ) Reachability Analysis and Control Barrier Functions (CBFs) provide rigorous safety assurances but often neglect performance, resulting in overly conservative controllers. To bridge this gap, we formulate the co-optimization of safety and performance as a state-constrained optimal control problem, where performance objectives are encoded via a cost function and safety requirements are imposed as state constraints. We demonstrate that the resultant value function satisfies a Hamilton-Jacobi-Bellman (HJB) equation, which we approximate efficiently using a novel physics-informed machine learning framework. In addition, we introduce a conformal prediction-based verification strategy to quantify the learning errors, recovering a high-confidence safety value function, along with a probabilistic error bound on performance degradation. Through several case studies, we demonstrate the efficacy of the proposed framework in enabling scalable learning of safe and performant controllers for complex, high-dimensional autonomous systems.

Deep Learning · Theory

Davide Sartor, Alberto Sinigaglia, Gian Antonio Susto

Imposing input-output constraints in multi-layer perceptrons (MLPs) plays a pivotal role in many real world applications. Monotonicity in particular is a common requirement in applications that need transparent and robust machine learning models. Conventional techniques for imposing monotonicity in MLPs by construction involve the use of non-negative weight constraints and bounded activation functions, which poses well known optimization challenges. In this work, we generalize previous theoretical results, showing that MLPs with non-negative weight constraint and activations that saturate on alternating sides are universal approximators for monotonic functions. Additionally, we show an equivalence between saturation side in the activations and sign of the weight constraint. This connection allows us to prove that MLPs with convex monotone activations and non-positive constrained weights also qualify as universal approximators, in contrast to their non-negative constrained counterparts. This results provide theoretical grounding to the empirical effectiveness observed in previous works, while leading to possible architectural simplification. Moreover, to further alleviate the optimization difficulties, we propose an alternative formulation that allows the network to adjust its activations according to the sign of the weights. This eliminates the requirement for weight reparameterization, easing initialization and improving training stability. Experimental evaluation reinforce the validity of the theoretical results, showing that our novel approach compares favorably to traditional monotonic architectures.