论文检索

Optimization · Convex

Chenrui Wang, Yixuan Qiu

The entropic-regularized optimal transport (OT) has gained massive attention in machine learning due to its ability to provide scalable solutions for OT-based tasks. However, most of the existing algorithms, including the Sinkhorn algorithm and its extensions, suffer from relatively slow convergence in many cases. More recently, some second-order methods have been proposed based on the idea of Hessian sparsification. Despite their promising results, they have two major issues: first, there is limited theoretical understanding on the effect of sparsification; second, in cases where the transport plan is dense, Hessian sparsification does not perform well. In this paper, we propose a new quasi-Newton method to address these problems. First, we develop new theoretical analyses to understand the benefits of Hessian sparsification, which lays the foundation for highly flexible sparsification schemes. Then we introduce an additional low-rank term in the approximate Hessian to better handle the dense case. Finally, the convergence properties of the proposed algorithm are rigorously analyzed, and various numerical experiments are conducted to demonstrate its improved performance in solving large-scale OT problems.

Optimization

Fabian Schaipp, Alexander Hägele, Adrien Taylor, Umut Simsekli, Francis Bach

We show that learning-rate schedules for large model training behave surprisingly similar to a performance bound from non-smooth convex optimization theory. We provide a bound for the constant schedule with linear cooldown; in particular, the practical benefit of cooldown is reflected in the bound due to the absence of logarithmic terms.Further, we show that this surprisingly close match between optimization theory and practice can be exploited for learning-rate tuning: we achieve noticeable improvements for training 124M and 210M Llama-type models by (i) extending the schedule for continued training with optimal learning-rate, and (ii) transferring the optimal learning-rate across schedules.

Optimization · Non-Convex

Ruichuan Huang, Jiawei Zhang, Ahmet Alacaoglu

We propose smoothed primal-dual algorithms for solving stochastic nonconvex optimization problems with linear \emph{inequality} constraints. Our algorithms are single-loop and only require a single (or two) samples of stochastic gradients at each iteration. A defining feature of our algorithm is that it is based on an inexact gradient descent framework for the Moreau envelope, where the gradient of the Moreau envelope is estimated using one step of a stochastic primal-dual (linearized) augmented Lagrangian algorithm. To handle inequality constraints and stochasticity, we combine the recently established global error bounds in constrained optimization with a Moreau envelope-based analysis of stochastic proximal algorithms. We establish the optimal (in their respective cases) $O(\varepsilon^{-4})$ and $O(\varepsilon^{-3})$ sample complexity guarantees for our algorithms and provide extensions to stochastic linear constraints. Unlike existing methods, iterations of our algorithms are free of subproblems, large batch sizes or increasing penalty parameters in their iterations and they use dual variable updates to ensure feasibility.

Optimization · Non-Convex

Songtao Lu

Extensive research has shown that a wide range of machine learning problems can be formulated as bilevel optimization, where two levels of learning processes intertwine through distinct sets of optimization variables. However, prevailing approaches often impose stringent assumptions, such as strong convexity of the lower-level loss function or uniqueness of the optimal solution, to enable algorithmic development and convergence analysis. However, these assumptions tend to be overly restrictive in real-world scenarios. In this work, we explore a recently popularized Moreau envelope based reformulation of bilevel optimization problems, accommodating nonconvex objective functions at both levels. We propose a stochastic primal-dual method that incorporates smoothing on both sides, capable of finding Karush-Kuhn-Tucker solutions for this general class of nonconvex bilevel optimization problems. A key feature of our algorithm is its ability to dynamically weigh the lower-level problems, enhancing its performance, particularly in stochastic learning scenarios. Numerical experiments underscore the superiority of our proposed algorithm over existing penalty-based methods in terms of both the convergence rate and the test accuracy.

Theory · Learning Theory

Shira Vansover-Hager, Tomer Koren, Roi Livni

We study the out-of-sample performance of multi-pass stochastic gradient descent (SGD) in the fundamental stochastic convex optimization (SCO) model. While one-pass SGD is known to achieve an optimal $\Theta(1/\sqrt{n})$ excess population loss given a sample of size $n$, much less is understood about the multi-pass version of the algorithm which is widely used in practice. Somewhat surprisingly, we show that in the general non-smooth case of SCO, just a few epochs of SGD can already hurt its out-of-sample performance significantly and lead to overfitting. In particular, using a step size $\eta = \Theta(1/\sqrt{n})$, which gives the optimal rate after one pass, can lead to population loss as large as $\Omega(1)$ after just one additional pass. More generally, we show that the population loss from the second pass onward is of the order $\Theta(1/(\eta T) + \eta \sqrt{T})$, where $T$ is the total number of steps. These results reveal a certain phase-transition in the out-of-sample behavior of SGD after the first epoch, as well as a sharp separation between the rates of overfitting in the smooth and non-smooth cases of SCO. Additionally, we extend our results to with-replacement SGD, proving that the same asymptotic bounds hold after $O(n \log n)$ steps. Finally, we also prove a lower bound of $\Omega(\eta \sqrt{n})$ on the generalization gap of one-pass SGD in dimension $d = {\widetilde O}(n)$, improving on recent results of Koren et al. (2022) and Schliserman et al. (2024).

Theory · Learning Theory

Weiwei Liu

High-dimensional inference addresses scenarios where the dimension of the data approaches, or even surpasses, the sample size. In these settings, the regularized $M$-estimator is a common technique for inferring parameters. (Negahban et al.,2009) establish a unified framework for establishing convergence rates in the context of high-dimensional scaling, demonstrating that estimation errors are confined within a restricted set, and revealing fast convergence rates. The key assumption underlying their work is the convexity of the loss function. However, many loss functions in high-dimensional contexts are nonconvex. This leads to the question: if the loss function is nonconvex, do estimation errors still fall within a restricted set? If yes, can we recover convergence rates of the estimation error under nonconvex situations? This paper provides affirmative answers to these critical questions.

Optimization · Convex

Ya-Chi Chu, Wenzhi Gao, Yinyu Ye, Madeleine Udell

This paper investigates the convergence properties of the hypergradient descent method ($\texttt{HDM}$), a 25-year-old heuristic originally proposed for adaptive stepsize selection in stochastic first-order methods. We provide the first rigorous convergence analysis of $\texttt{HDM}$ using the online learning framework and apply this analysis to develop a new state-of-the-art adaptive gradient methods with empirical and theoretical support. Notably, $\texttt{HDM}$ automatically identifies the optimal stepsize for the local optimization landscape and achieves local superlinear convergence. Our analysis explains the instability of $\texttt{HDM}$ reported in the literature and proposes efficient strategies to address it. We also develop two $\texttt{HDM}$ variants with heavy-ball and Nesterov momentum. Experiments on deterministic convex problems show $\texttt{HDM}$ with heavy-ball momentum ($\texttt{HDM-HB}$) exhibits robust performance and significantly outperforms other adaptive first-order methods. Moreover, $\texttt{HDM-HB}$ often matches the performance of $\texttt{L-BFGS}$, an efficient and practical quasi-Newton method, using less memory and cheaper iterations.

Optimization · Large Scale, Parallel and Distributed

Geon-Woo Kim, Junbo Li, Shashidhar Gandham, Omar Baldonado, Adithya Gangidi, Pavan Balaji, Zhangyang “Atlas” Wang, Aditya Akella

Training large language models (LLMs) increasingly relies on geographically distributed accelerators, causing prohibitive communication costs across regions and uneven utilization of heterogeneous hardware. We propose HALoS, a hierarchical asynchronous optimization framework that tackles these issues by introducing local parameter servers (LPSs) within each region and a global parameter server (GPS) that merges updates across regions. This hierarchical design minimizes expensive inter-region communication, reduces straggler effects, and leverages fast intra-region links. We provide a rigorous convergence analysis for HALoS under non-convex objectives, including theoretical guarantees on the role of hierarchical momentum in asynchronous training. Empirically, HALoS attains up to 7.5× faster convergence than synchronous baselines in geo-distributed LLM training and improves upon existing asynchronous methods by up to 2.1×. Crucially, HALoS preserves the model quality of fully synchronous SGD—matching or exceeding accuracy on standard language modeling and downstream benchmarks—while substantially lowering total training time. These results demonstrate that hierarchical, server-side update accumulation and global model merging are powerful tools for scalable, efficient training of new-era LLMs in heterogeneous, geo-distributed environments.

Optimization

Sharan Vaswani, Reza Babanezhad

Armijo line-search (Armijo-LS) is a standard method to set the step-size for gradient descent (GD). For smooth functions, Armijo-LS alleviates the need to know the global smoothness constant $L$ and adapts to the ``local'' smoothness, enabling GD to converge faster. Existing theoretical analyses show that GD with Armijo-LS ($\texttt{GD-LS}$) can result in constant factor improvements over GD with a $1/L$ step-size (denoted as $\texttt{GD(1/L)}$). We strengthen these results and show that if the objective function satisfies a certain non-uniform smoothness condition, $\texttt{GD-LS}$ can result in a faster convergence rate than $\texttt{GD(1/L)}$. In particular, we prove that for convex objectives corresponding to logistic regression and multi-class classification, $\texttt{GD-LS}$ can converge to the optimum at a linear rate, and hence improves over the sublinear convergence of $\texttt{GD(1/L)}$. Furthermore, for non-convex objectives satisfying gradient domination (e.g., those corresponding to the softmax policy gradient in RL or generalized linear models with a logistic link function), $\texttt{GD-LS}$ can match the fast convergence of algorithms tailored for these specific settings. Finally, we prove that under the interpolation assumption, for convex losses, stochastic GD with a stochastic line-search can match the fast convergence of $\texttt{GD-LS}$.

Probabilistic Methods · Bayesian Models and Methods

Parikshit Pareek, Abhijith Jayakumar, Kaarthik Sundar, Sidhant Misra, Deepjyoti Deka

Constrained optimization problems arise in various engineering systems such as inventory management and power grids. Standard deep neural network (DNN) based machine learning proxies are ineffective in practical settings where labeled data is scarce and training times are limited. We propose a semi-supervised Bayesian Neural Networks (BNNs) based optimization proxy for this complex regime, wherein training commences in a sandwiched fashion, alternating between a supervised learning step for minimizing cost, and an unsupervised learning step for enforcing constraint feasibility. We show that the proposed semi-supervised BNN outperforms DNN architectures on important non-convex constrained optimization problems from energy network operations, achieving up to a tenfold reduction in expected maximum equality gap and halving the inequality gaps. Further, the BNN's ability to provide posterior samples is leveraged to construct practically meaningful probabilistic confidence bounds on performance using a limited validation data, unlike prior methods.

Optimization · Non-Convex

Peng Wang, Yifu Lu, Yaodong Yu, Druv Pai, Qing Qu, Yi Ma

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer architectures may be redundant. To derive a fully interpretable transformer architecture with only necessary components, we contend that the goal of representation learning is to compress a set of noisy initial token representations towards a mixture of low-dimensional subspaces. To compress these noisy token representations, an associated denoising operation naturally takes the form of a multi-head (subspace) self-attention. By unrolling such iterative denoising operations into a deep network, we arrive at a highly compact architecture that consists of \textit{only} self-attention operators with skip connections at each layer. Moreover, we show that each layer performs highly efficient denoising: it improves the signal-to-noise ratio of token representations \textit{at a linear rate} with respect to the number of layers. Despite its simplicity, extensive experiments on vision and language tasks demonstrate that such a transformer achieves performance close to that of standard transformer architectures such as GPT-2 and CRATE.

Deep Learning

Ekaterina Filimoshina, Dmitry Shirokov

We propose, implement, and compare with competitors a new architecture of equivariant neural networks based on geometric (Clifford) algebras: Generalized Lipschitz Group Equivariant Neural Networks (GLGENN). These networks are equivariant to all pseudo-orthogonal transformations, including rotations and reflections, of a vector space with any non-degenerate or degenerate symmetric bilinear form. We propose a weight-sharing parametrization technique that takes into account the fundamental structures and operations of geometric algebras. Due to this technique, GLGENN architecture is parameter-light and has less tendency to overfitting than baseline equivariant models. GLGENN outperforms or matches competitors on several benchmarking equivariant tasks, including estimation of an equivariant function and a convex hull experiment, while using significantly fewer optimizable parameters.

Optimization · Discrete and Combinatorial Optimization

George Orfanides, Tim Hoheisel, Marwa El Halabi

Submodular functions, defined on continuous or discrete domains, arise in numerous applications. We study the minimization of the difference of submodular (DS) functions, over both domains, extending prior work restricted to set functions.We show that all functions on discrete domains and all smooth functions on continuous domains are DS. For discrete domains, we observe that DS minimization is equivalent to minimizing the difference of two convex (DC) functions, as in the set function case. We propose a novel variant of the DC Algorithm (DCA) and apply it to the resulting DC Program, obtaining comparable theoretical guarantees as in the set function case. The algorithm can be applied to continuous domains via discretization. Experiments demonstrate that our method outperforms baselines in integer compressive sensing and integer least squares.

General Machine Learning · Supervised Learning

Magzhan Gabidolla, Miguel Carreira-Perpinan

We explore ensembles of axis-aligned decision stumps, which can be viewed as a generalized additive model (GAM). In this model, stumps utilizing the same feature are grouped to form a shape function for that feature. Instead of relying on boosting or bagging, we employ alternating optimization to learn a fixed-size stump forest. We optimize the parameters of each stump exactly through enumeration, given the other stumps are fixed. For fixed stump splits, the leaf values are optimized jointly by solving a convex problem. To address the overfitting issue inherent in naive optimization of stump forests, we propose effective regularization techniques. Our regularized stump forests achieve accuracy comparable to state-of-the-art GAM methods while using fewer parameters. This work is the first to successfully learn stump forests without employing traditional ensembling techniques like bagging or boosting.

Social Aspects · Accountability, Transparency, and Interpretability

Thomas Fel, Ekdeep Singh Lubana, Jacob Prince, Matthew Kowal, Victor Boutin, Isabel Papadimitriou, Binxu Wang, Martin Wattenberg, Demba Ba, Talia Konkle

Sparse Autoencoders (SAEs) have emerged as a powerful framework for machine learning interpretability, enabling the unsupervised decomposition of model representations into a dictionary of abstract, human-interpretable concepts. However, we reveal a fundamental limitation: SAEs exhibit severe instability, as identical models trained on similar datasets can produce sharply different dictionaries, undermining their reliability as an interpretability tool. To address this issue, we draw inspiration from the Archetypal Analysis framework introduced by Cutler & Breiman (1994) and present Archetypal SAEs (A-SAE), wherein dictionary atoms are constrained to the data’s convex hull. This geometric anchoring significantly enhances the stability and plausibility of inferred dictionaries, and their mildly relaxed variants RA-SAEs further match state-of-the-art reconstruction abilities. To rigorously assess dictionary quality learned by SAEs, we introduce two new benchmarks that test (i) plausibility, if dictionaries recover “true” classification directions and (ii) identifiability, if dictionaries disentangle synthetic concept mixtures. Across all evaluations, RA-SAEs consistently yield more structured representations while uncovering novel, semantically meaningful concepts in large-scale vision models.

Kwangjun Ahn, Gagik Magakyan, Ashok Cutkosky

This work investigates the effectiveness of schedule-free methods, developed by A. Defazio et al. (NeurIPS 2024), in nonconvex optimization settings, inspired by their remarkable empirical success in training neural networks. Specifically, we show that schedule-free SGD achieves optimal iteration complexity for nonsmooth, non-convex optimization problems. Our proof begins with the development of a general framework for online-to-nonconvex conversion, which converts a given online learning algorithm into an optimization algorithm for nonconvex losses. Our general framework not only recovers existing conversions but also leads to two novel conversion schemes. Notably, one of these new conversions corresponds directly to schedule-free SGD, allowing us to establish its optimality. Additionally, our analysis provides valuable insights into the parameter choices for schedule-free SGD, addressing a theoretical gap that the convex theory cannot explain.

Konstantinos Oikonomidis, Jan Quan, Emanuel Laude, Panagiotis Patrinos

We analyze nonlinearly preconditioned gradient methods for solving smooth minimization problems. We introduce a generalized smoothness property, based on the notion of abstract convexity, that is broader than Lipschitz smoothness and provide sufficient first- and second-order conditions. Notably, our framework encapsulates algorithms associated with the gradient clipping method and brings out novel insights for the class of $(L_0,L_1)$-smooth functions that has received widespread interest recently, thus allowing us to extend beyond already established methods. We investigate the convergence of the proposed method in both the convex and nonconvex setting.

General Machine Learning

Florian Beier, Moritz Piening, Robert Beinert, Gabriele Steidl

We propose a new approach for unsupervised alignment of heterogeneous datasets, which maps data from two different domains without any known correspondences to a common metric space. Our method is based on an unbalanced optimal transport problem with Gromov-Wasserstein marginal penalization. It can be seen as a counterpart to the recently introduced joint multidimensional scaling method. We prove that there exists a minimizer of our functional and that for penalization parameters going to infinity, the corresponding sequence of minimizers converges to a minimizer of the so-called embedded Wasserstein distance. Our model can be reformulated as a quadratic, multi-marginal, unbalanced optimal transport problem, for which a bi-convex relaxation admits a numerical solver via block-coordinate descent. We provide numerical examples for joint embeddings in Euclidean as well as non-Euclidean spaces.

Optimization · Convex

Rahul Choudhary, Hanbaek Lyu

The classical static Schrödinger Bridge (SSB) problem, which seeks the most likely stochastic evolution between two marginal probability measures, has been studied extensively in the optimal transport and statistical physics communities, and more recently in machine learning communities in the surge of generative models. The standard approach to solve SSB is to first identify its Kantorovich dual and use Sinkhorn's algorithm to find the optimal potential functions. While the original SSB is only a strictly convex minimization problem, this approach is known to warrant linear convergence under mild assumptions. In this work, we consider a generalized SSB allowing any strictly increasing divergence functional, far generalizing the entropy functional $x\log x$ in the standard SSB. This problem naturally arises in a wide range of seemingly unrelated problems in entropic optimal transport, random graphs/matrices, and combinatorics. We establish Kantorovich duality and linear convergence of Sinkhorn's algorithm for the generalized SSB problem under mild conditions. Our results provide a new rigorous foundation for understanding Sinkhorn-type iterative methods in the context of large-scale generalized Schrödinger bridges.

Theory · Online Learning and Bandits

Xiaoyu Wang, Wenhao Yang, Chang Yao, Mingli Song, Yuanyu Wan

Although the differential privacy (DP) of decentralized online learning has garnered considerable attention recently, existing algorithms are unsatisfactory due to their inability to achieve $(\epsilon, 0)$-DP over all $T$ rounds, recover the optimal regret in the non-private case, and maintain the lightweight computation under complex constraints. To address these issues, we first propose a new decentralized online learning algorithm satisfying $(\epsilon, 0)$-DP over $T$ rounds, and show that it can achieve $\widetilde{O}(n(\rho^{-1/4}+\epsilon^{-1}\rho^{1/4})\sqrt{T})$ and $\widetilde{O}(n (\rho^{-1/2}+\epsilon^{-1}))$ regret bounds for convex and strongly convex functions respectively, where $n$ is the number of local learners and $\rho$ is the spectral gap of the communication matrix. As long as $\epsilon=\Omega(\sqrt{\rho})$, these bounds nearly match existing lower bounds in the non-private case, which implies that $(\epsilon, 0)$-DP of decentralized online learning may be ensured nearly for free. Our key idea is to design a block-decoupled accelerated gossip strategy that can be incorporated with the classical tree-based private aggregation, and also enjoys a faster average consensus among local learners. Furthermore, we develop a projection-free variant of our algorithm to keep the efficiency under complex constraints. As a trade-off, the above regret bounds degrade to $\widetilde{O}(n(T^{3/4}+\epsilon^{-1}T^{1/4}))$ and $\widetilde{O}(n(T^{2/3}+\epsilon^{-1}))$ respectively, which however are even better than the existing private centralized projection-free online algorithm.