论文检索

Optimization · Bilevel optimization

Jeongyeol Kwon, Dohyun Kwon, Hanbaek Lyu

We consider the problem of finding stationary points in Bilevel optimization when the lower-level problem is unconstrained and strongly convex. The problem has been extensively studied in recent years; the main technical challenge is to keep track of lower-level solutions $y^*(x)$ in response to the changes in the upper-level variables $x$. Subsequently, all existing approaches tie their analyses to a genie algorithm that knows lower-level solutions and, therefore, need not query any points far from them. We consider a dual question to such approaches: suppose we have an oracle, which we call $y^*$-aware, that returns an $O(\epsilon)$-estimate of the lower-level solution, in addition to first-order gradient estimators *locally unbiased* within the $\Theta(\epsilon)$-ball around $y^*(x)$. We study the complexity of finding stationary points with such an $y^*$-aware oracle: we propose a simple first-order method that converges to an $\epsilon$ stationary point using $O(\epsilon^{-6}), O(\epsilon^{-4})$ access to first-order $y^*$-aware oracles. Our upper bounds also apply to standard unbiased first-order oracles, improving the best-known complexity of first-order methods by $O(\epsilon)$ with minimal assumptions. We then provide the matching $\Omega(\epsilon^{-6})$, $\Omega(\epsilon^{-4})$ lower bounds without and with an additional smoothness assumption, respectively. Our results imply that any approach that simulates an algorithm with an $y^*$-aware oracle must suffer the same lower bounds.

Optimization · First-order

Nadav Hallak, Kfir Levy

This paper studies the theoretical guarantees of the classical projected gradient and conditional gradient methods applied to constrained optimization problems with biased relative-error gradient oracles. These oracles are used in various settings, such as distributed optimization systems or derivative-free optimization, and are particularly common when gradients are compressed, quantized, or estimated via finite differences computations. Several settings are investigated: Optimization over the box with a coordinate-wise erroneous gradient oracle, optimization over a general compact convex set, and three more specific scenarios. Convergence guarantees are established with respect to the relative-error magnitude, and in particular, we show that the conditional gradient is invariant to relative-error when applied over the box with a coordinate-wise erroneous gradient oracle, and the projected gradient maintains its convergence guarantees when optimizing a nonconvex objective function.

Theory · Learning Theory

Yi-Fan Zhang, Min-Ling Zhang

Despite great advances in algorithms for multi-label learning, research on the theoretical analysis of generalization is still in the early stage. Some recent theoretical results has investigated the generalization performance of multi-label learning under several evaluation metrics, however, how to reduce the dependency on the number of labels, explicitly introduce label correlations, and quantitatively analyze the impact of various inductive biases in the generalization analysis of multi-label learning is still a crucial and open problem. In an attempt to make up for the gap in the generalization theory of multi-label learning, we develop several novel vector-contraction inequalities, which exploit the Lipschitz continuity of loss functions, and derive generalization bounds with a weaker dependency on the number of labels than the state of the art in the case of decoupling the relationship among different components, which serves as theoretical guarantees for the generalization of multi-label learning. In addition, we derive the generalization bound for Macro-Averaged AUC and analyze its relationship with class-imbalance. The mild bounds without strong assumptions explain the good generalization ability of multi-label learning with first-order label correlations and high-order label correlations induced by norm regularizers.

Miscellaneous Aspects of Machine Learning · General Machine Learning Techniques

Ilya Kaufman, Omri Azencot

Data augmentation (DA) methods tailored to specific domains generate synthetic samples by applying transformations that are appropriate for the characteristics of the underlying data domain, such as rotations on images and time warping on time series data. In contrast, *domain-independent* approaches, e.g. *mixup*, are applicable to various data modalities, and as such they are general and versatile. While regularizing classification tasks via DA is a well-explored research topic, the effect of DA on regression problems received less attention. To bridge this gap, we study the problem of domain-independent augmentation for regression, and we introduce *FOMA*: a new data-driven domain-independent data augmentation method. Essentially, our approach samples new examples from the tangent planes of the train distribution. Augmenting data in this way aligns with the network tendency towards capturing the dominant features of its input signals. We evaluate *FOMA* on in-distribution generalization and out-of-distribution robustness benchmarks, and we show that it improves the generalization of several neural architectures. We also find that strong baselines based on *mixup* are less effective in comparison to our approach. Our code is publicly available at https://github.com/azencot-group/FOMA

Optimization · Zero-order and Black-box Optimization

Tanmay Gautam, Youngsuk Park, Hao Zhou, Parameswaran Raman, Wooseok Ha

Fine-tuning language models (LMs) has demonstrated success in a wide array of downstream tasks. However, as LMs are scaled up, the memory requirements for backpropagation become prohibitively high. Zeroth-order (ZO) optimization methods can leverage memory-efficient forward passes to estimate gradients. More recently, MeZO, an adaptation of ZO-SGD, has been shown to consistently outperform zero-shot and in-context learning when combined with suitable task prompts. In this work, we couple ZO methods with variance reduction techniques to enhance stability and convergence for inference-based LM fine-tuning. We introduce Memory-Efficient Zeroth-Order Stochastic Variance-Reduced Gradient (MeZO-SVRG) and demonstrate its efficacy across multiple LM fine-tuning tasks, eliminating the reliance on task-specific prompts. Evaluated across a range of both masked and autoregressive LMs on benchmark GLUE tasks, MeZO-SVRG outperforms MeZO with up to 20% increase in test accuracies in both full- and partial-parameter fine-tuning settings. MeZO-SVRG benefits from reduced computation time as it often surpasses MeZO's peak test accuracy with a $2\times$ reduction in GPU-hours. MeZO-SVRG significantly reduces the required memory footprint compared to first-order SGD, i.e. by $2\times$ for autoregressive models. Our experiments highlight that MeZO-SVRG's memory savings progressively improve compared to SGD with larger batch sizes.

Reinforcement Learning · Batch/Offline

Yun-Hsuan Lien, Ping-Chun Hsieh, Tzu-Mao Li, Yu-Shuen Wang

In offline reinforcement learning (RL), updating the value function with the discrete-time Bellman Equation often encounters challenges due to the limited scope of available data. This limitation stems from the Bellman Equation, which cannot accurately predict the value of unvisited states. To address this issue, we have introduced an innovative solution that bridges the continuous- and discrete-time RL methods, capitalizing on their advantages. Our method uses a discrete-time RL algorithm to derive the value function from a dataset while ensuring that the function's first derivative aligns with the local characteristics of states and actions, as defined by the Hamilton-Jacobi-Bellman equation in continuous RL. We provide practical algorithms for both deterministic policy gradient methods and stochastic policy gradient methods. Experiments on the D4RL dataset show that incorporating the first-order information significantly improves policy performance for offline RL problems.

Deep Learning · Generative Models and Autoencoders

Kaiwen Xue, Yuhao Zhou, Shen Nie, Xu Min, Xiaolu Zhang, JUN ZHOU, Chongxuan Li

Bayesian flow networks (BFNs) iteratively refine the parameters, instead of the samples in diffusion models (DMs), of distributions at various noise levels through Bayesian inference. Owing to its differentiable nature, BFNs are promising in modeling both continuous and discrete data, while simultaneously maintaining fast sampling capabilities. This paper aims to understand and enhance BFNs by connecting them with DMs through stochastic differential equations (SDEs). We identify the linear SDEs corresponding to the noise-addition processes in BFNs, demonstrate that BFN's regression losses are aligned with denoise score matching, and validate the sampler in BFN as a first-order solver for the respective reverse-time SDE. Based on these findings and existing recipes of fast sampling in DMs, we propose specialized solvers for BFNs that markedly surpass the original BFN sampler in terms of sample quality with a limited number of function evaluations (e.g., 10) on both image and text datasets. Notably, our best sampler achieves an increase in speed of $5\sim20$ times for free.

Optimization

William Powell, Hanbaek Lyu

For obtaining optimal first-order convergence guarantees for stochastic optimization, it is necessary to use a recurrent data sampling algorithm that samples every data point with sufficient frequency. Most commonly used data sampling algorithms (e.g., i.i.d., MCMC, random reshuffling) are indeed recurrent under mild assumptions. In this work, we show that for a particular class of stochastic optimization algorithms, we do not need any further property (e.g., independence, exponential mixing, and reshuffling) beyond recurrence in data sampling to guarantee optimal rate of first-order convergence. Namely, using regularized versions of Minimization by Incremental Surrogate Optimization (MISO), we show that for non-convex and possibly non-smooth objective functions with constraints, the expected optimality gap converges at an optimal rate $O(n^{-1/2})$ under general recurrent sampling schemes. Furthermore, the implied constant depends explicitly on the 'speed of recurrence', measured by the expected amount of time to visit a data point, either averaged ('target time') or supremized ('hitting time') over the starting locations. We discuss applications of our general framework to decentralized optimization and distributed non-negative matrix factorization.

Reinforcement Learning · Deep RL

Ignat Georgiev, Krishnan Srinivasan, Jie Xu, Eric Heiden, Animesh Garg

Model-Free Reinforcement Learning (MFRL), leveraging the policy gradient theorem, has demonstrated considerable success in continuous control tasks. However, these approaches are plagued by high gradient variance due to zeroth-order gradient estimation, resulting in suboptimal policies. Conversely, First-Order Model-Based Reinforcement Learning (FO-MBRL) methods employing differentiable simulation provide gradients with reduced variance but are susceptible to sampling error in scenarios involving stiff dynamics, such as physical contact. This paper investigates the source of this error and introduces Adaptive Horizon Actor-Critic (AHAC), an FO-MBRL algorithm that reduces gradient error by adapting the model-based horizon to avoid stiff dynamics. Empirical findings reveal that AHAC outperforms MFRL baselines, attaining 40% more reward across a set of locomotion tasks and efficiently scaling to high-dimensional control environments with improved wall-clock-time efficiency. [adaptive-horizon-actor-critic.github.io](https://adaptive-horizon-actor-critic.github.io/)

Optimization · First-order

Kyuwon Kim, Donghwan Kim

In nonconvex-nonconcave minimax optimization, two-timescale gradient methods have shown their potential to find local minimax (optimal) points, provided that the timescale separation between the min and the max player is sufficiently large. However, existing two-timescale variants of gradient descent ascent and extragradient methods face two shortcomings, especially when we search for non-strict local minimax points that are prevalent in modern overparameterized setting. In specific, (1) these methods can be unstable at some non-strict local minimax points even with sufficiently large timescale separation, and even (2) computing a proper amount of timescale separation is infeasible in practice. To remedy these two issues, we propose to incorporate two simple but provably effective schemes, double-step alternating update and increasing timescale separation, into the two-timescale extragradient method, respectively. Under mild conditions, we show that the proposed methods converge to non-strict local minimax points that all existing two-timescale methods fail to converge.

Optimization · Zero-order and Black-box Optimization

Yihua Zhang, Pingzhi Li, Junyuan Hong, Jiaxiang Li, Yimeng Zhang, Wenqing Zheng, Pin-Yu Chen, Jason Lee, Wotao Yin, Mingyi Hong 等

In the evolving landscape of natural language processing (NLP), fine-tuning pre-trained Large Language Models (LLMs) with first-order (FO) optimizers like SGD and Adam has become standard. Yet, as LLMs grow in size, the substantial memory overhead from back-propagation (BP) for FO gradient computation presents a significant challenge. Addressing this issue is crucial, especially for applications like on-device training where memory efficiency is paramount. This paper proposes a shift towards BP-free, zeroth-order (ZO) optimization as a solution for reducing memory costs during LLM fine-tuning, building on the initial concept introduced by (Malladi et al., 2023). Unlike traditional ZO-SGD methods, ou让work expands the exploration to a wider array of ZO optimization techniques, through a comprehensive, first-of-its-kind benchmarking study across five LLM families, three task complexities, and five fine-tuning schemes. Our study unveils previously overlooked optimization principles, highlighting the importance of task alignment, the role of the forward gradient method, and the balance between algorithm complexity and fine-tuning performance. We further introduce novel enhancements to ZO optimization, including block-wise descent, hybrid training, and gradient sparsity. Our study offers a promising direction for achieving further memory-efficient LLM fine-tuning. Codes to reproduce all our experiments will be made public.

Reinforcement Learning

Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti

Recent works have studied *state entropy maximization* in reinforcement learning, in which the agent's objective is to learn a policy inducing high entropy over states visitation (Hazan et al., 2019). They typically assume full observability of the state of the system, so that the entropy of the observations is maximized. In practice, the agent may only get *partial* observations, e.g., a robot perceiving the state of a physical space through proximity sensors and cameras. A significant mismatch between the entropy over observations and true states of the system can arise in those settings. In this paper, we address the problem of entropy maximization over the *true states* with a decision policy conditioned on partial observations *only*. The latter is a generalization of POMDPs, which is intractable in general. We develop a memory and computationally efficient *policy gradient* method to address a first-order relaxation of the objective defined on *belief* states, providing various formal characterizations of approximation gaps, the optimization landscape, and the *hallucination* problem. This paper aims to generalize state entropy maximization to more realistic domains that meet the challenges of applications.

Optimization · Non-Convex

Oscar Smee, Fred Roosta

We consider solving large scale nonconvex optimisation problems with nonnegativity constraints. Such problems arise frequently in machine learning, such as nonnegative least-squares, nonnegative matrix factorisation, as well as problems with sparsity-inducing regularisation. In such settings, first-order methods, despite their simplicity, can be prohibitively slow on ill-conditioned problems or become trapped near saddle regions, while most second-order alternatives involve non-trivially challenging subproblems. The two-metric projection framework, initially proposed by Bertsekas (1982), alleviates these issues and achieves the best of both worlds by combining projected gradient steps at the boundary of the feasible region with Newton steps in the interior in such a way that feasibility can be maintained by simple projection onto the nonnegative orthant. We develop extensions of the two-metric projection framework, which by inexactly solving the subproblems as well as employing non-positive curvature directions, are suitable for large scale and nonconvex settings. We obtain state-of-the-art convergence rates for various classes of non-convex problems and demonstrate competitive practical performance on a variety of problems.

Optimization · Learning for Optimization

Saurabh Mishra, Anant Raj, Sharan Vaswani

Inverse optimization involves inferring unknown parameters of an optimization problem from known solutions and is widely used in fields such as transportation, power systems, and healthcare. We study the *contextual inverse optimization setting* that utilizes additional contextual information to better predict the unknown problem parameters. We focus on contextual inverse linear programming (CILP) addressing the challenges posed by the non-differentiable nature of LPs. For a linear prediction model, we reduce CILP to a convex feasibility problem allowing the use of standard algorithms such as alternating projections. The resulting algorithm for CILP is equipped with theoretical convergence guarantees without additional assumptions such as degeneracy or interpolation. Next, we reduce CILP to empirical risk minimization (ERM) on a smooth, convex loss that satisfies the Polyak-Lojasiewicz condition. This reduction enables the use of scalable first-order optimization methods to solve large non-convex problems while maintaining theoretical guarantees in the convex setting. Subsequently, we use the reduction to ERM to quantify the generalization performance of the proposed algorithm on previously unseen instances. Finally, we experimentally validate our approach on synthetic and real-world problems and demonstrate improved performance compared to existing methods.

Optimization · First-order

David Martínez-Rubio, Christophe Roux, Sebastian Pokutta

In this work, we analyze two of the most fundamental algorithms in geodesically convex optimization: Riemannian gradient descent and (possibly inexact) Riemannian proximal point. We quantify their rates of convergence and produce different variants with several trade-offs. Crucially, we show the iterates naturally stay in a ball around an optimizer, of radius depending on the initial distance and, in some cases, on the curvature. Previous works simply assumed bounded iterates, resulting in rates that were not fully quantified. We also provide an implementable inexact proximal point algorithm and prove several new useful properties of Riemannian proximal methods: they work when positive curvature is present, the proximal operator does not move points away from any optimizer, and we quantify the smoothness of its induced Moreau envelope. Further, we explore beyond our theory with empirical tests.

Deep Learning · Sequential Models, Time series

Maude Lizaire, Michael Rizvi-Martel, Marawan Gamal, Guillaume Rabusseau

Second-order Recurrent Neural Networks (2RNNs) extend RNNs by leveraging second-order interactions for sequence modelling. These models are provably more expressive than their first-order counterparts and have connections to well-studied models from formal language theory. However, their large parameter tensor makes computations intractable. To circumvent this issue, one approach known as MIRNN consists in limiting the type of interactions used by the model. Another is to leverage tensor decomposition to diminish the parameter count. In this work, we study the model resulting from parameterizing 2RNNs using the CP decomposition, which we call CPRNN. Intuitively, the rank of the decomposition should reduce expressivity. We analyze how rank and hidden size affect model capacity and show the relationships between RNNs, 2RNNs, MIRNNs, and CPRNNs based on these parameters. We support these results empirically with experiments on the Penn Treebank dataset which demonstrate that, with a fixed parameter budget, CPRNNs outperforms RNNs, 2RNNs, and MIRNNs with the right choice of rank and hidden size.

Optimization · Bilevel optimization

Risheng Liu, Zhu Liu, Wei Yao, Shangzhi Zeng, Jin Zhang

This work focuses on addressing two major challenges in the context of large-scale nonconvex Bi-Level Optimization (BLO) problems, which are increasingly applied in machine learning due to their ability to model nested structures. These challenges involve ensuring computational efficiency and providing theoretical guarantees. While recent advances in scalable BLO algorithms have primarily relied on lower-level convexity simplification, our work specifically tackles large-scale BLO problems involving nonconvexity in both the upper and lower levels. We simultaneously address computational and theoretical challenges by introducing an innovative single-loop gradient-based algorithm, utilizing the Moreau envelope-based reformulation, and providing non-asymptotic convergence analysis for general nonconvex BLO problems. Notably, our algorithm relies solely on first-order gradient information, enhancing its practicality and efficiency, especially for large-scale BLO learning tasks. We validate our approach's effectiveness through experiments on various synthetic problems, two typical hyper-parameter learning tasks, and a real-world neural architecture search application, collectively demonstrating its superior performance.

Optimization · First-order

Yuchen Li, Laura Balzano, Deanna Needell, Hanbaek Lyu

We analyze inexact Riemannian gradient descent (RGD) where Riemannian gradients and retractions are inexactly (and cheaply) computed. Our focus is on understanding when inexact RGD converges and what is the complexity in the general nonconvex and constrained setting. We answer these questions in a general framework of tangential Block Majorization-Minimization (tBMM). We establish that tBMM converges to an $\epsilon$-stationary point within $O(\epsilon^{-2})$ iterations. Under a mild assumption, the results still hold when the subproblem is solved inexactly in each iteration provided the total optimality gap is bounded. Our general analysis applies to a wide range of classical algorithms with Riemannian constraints including inexact RGD and proximal gradient method on Stiefel manifolds. We numerically validate that tBMM shows improved performance over existing methods when applied to various problems, including nonnegative tensor decomposition with Riemannian constraints, regularized nonnegative matrix factorization, and low-rank matrix recovery problems.

Optimization

Andreas Kontogiannis, Vasilis Pollatos, Sotiris Kanellopoulos, Panayotis Mertikopoulos, Aris Pagourtzis, Ioannis Panageas

Non-convex minimization problems are universally considered hard, and even guaranteeing that a computed solution is locally minimizing is known to be NP-hard. In this general context, our paper focuses on the problem of finding stationary points that satisfy an approximate second-order optimality condition, which serves to exclude strict saddles and other non-minimizing stationary points. Our main result is that the problem of finding approximate second-order stationary points (SOSPs) is PLS-complete, i.e., of the same complexity as the problem of finding first-order stationary points (FOSPs), thus resolving an open question in the field. In particular, our results imply that, under the widely believed complexity conjecture that PLS $\neq$ FNP, finding approximate SOSPs in unconstrained domains is *easier* than in constrained domains, which is known to be NP-hard. This comes in stark contrast with earlier results which implied that, unless PLS = CLS, finding approximate FOSPs in unconstrained domains is *harder* than in constrained domains.

Deep Learning · Theory

Taeyoung Kim, Hongseok Yang

The recent theoretical analysis of deep neural networks in their infinite-width limits has deepened our understanding of initialisation, feature learning, and training of those networks, and brought new practical techniques for finding appropriate hyperparameters, learning network weights, and performing inference. In this paper, we broaden this line of research by showing that this infinite-width analysis can be extended to the Jacobian of a deep neural network. We show that a multilayer perceptron (MLP) and its Jacobian at initialisation jointly converge to a Gaussian process (GP) as the widths of the MLP's hidden layers go to infinity and characterise this GP. We also prove that in the infinite-width limit, the evolution of the MLP under the so-called robust training (i.e., training with a regulariser on the Jacobian) is described by a linear first-order ordinary differential equation that is determined by a variant of the Neural Tangent Kernel. We experimentally show the relevance of our theoretical claims to wide finite networks, and empirically analyse the properties of kernel regression solution to obtain an insight into Jacobian regularisation.