论文检索

Optimization · Non-Convex

Kaiyi Ji

Although upper bound guarantees for bilevel optimization have been widely studied, progress on lower bounds has been limited due to the complexity of the bilevel structure. In this work, we focus on the smooth nonconvex-strongly-convex setting and develop new hard instances that yield nontrivial lower bounds under deterministic and stochastic first-order oracle models. In the deterministic case, we prove that any first-order zero-respecting algorithm requires at least $\Omega(\kappa^{3/2}\epsilon^{-2})$ oracle calls to find an $\epsilon$-accurate stationary point, improving the optimal lower bounds known for single-level nonconvex optimization and for nonconvex-strongly-convex min-max problems. In the stochastic case, we show that at least $\Omega(\kappa^{5/2}\epsilon^{-4})$ stochastic oracle calls are necessary, again strengthening the best known bounds in related settings. Our results expose substantial gaps between current upper and lower bounds for bilevel optimization and suggest that even simplified regimes, such as those with quadratic lower-level objectives, warrant further investigation toward understanding the optimal complexity of bilevel optimization under standard first-order oracles.

Optimization · Stochastic

Kevin Kurian Thomas Vaidyan, Michael Friedlander, Ahmet Alacaoglu

We analyze two classical algorithms for solving additively composite convex optimization problems where the objective is the sum of a smooth term and a nonsmooth regularizer: proximal stochastic gradient method for a single regularizer; and the randomized incremental proximal method, which uses the proximal operator of a randomly selected function when the regularizer is given as the sum of many nonsmooth functions. We focus on relaxing the bounded variance assumption that is common, yet stringent, for getting last iterate convergence rates. We prove the $\widetilde{O}(1/\sqrt{T})$ rate of convergence for the last iterate of both algorithms under componentwise convexity and smoothness, which is optimal up to log terms. Our results apply directly to graph-guided regularizers that arise in multi-task and federated learning, where the regularizer decomposes as a sum over edges of a collaboration graph.

Optimization · Stochastic

Feng Zhu, Robert Heath, Aritra Mitra

Stochastic variance-reduced algorithms such as Stochastic Average Gradient (SAG) and SAGA, and their deterministic counterparts like the Incremental Aggregated Gradient (IAG) method, have been extensively studied in large-scale machine learning. Despite their popularity, existing analyses for these algorithms are disparate, relying on different proof techniques tailored to each method. Furthermore, the original proof of SAG is known to be notoriously involved, requiring computer-aided analysis. Focusing on finite-sum optimization with smooth and strongly convex objectives, our main contribution is to develop a single unified convergence analysis that applies to all three algorithms: SAG, SAGA, and IAG. Our analysis features two key steps: (i) establishing a bound on delays due to sub-sampling using simple concentration tools, and (ii) carefully designing a novel Lyapunov function that accounts for such delays. The resulting proof is short and modular, providing high-probability bounds for SAG and SAGA that can be seamlessly extended to non-convex objectives and Markovian sampling. As an immediate byproduct of our new analysis technique, we obtain the best known rates for the IAG algorithm, significantly improving upon prior bounds.

Optimization · Stochastic

Aleksandr Shestakov, Martin Takac, Eduard Gorbunov

Gradient clipping is widely used to stabilize stochastic gradient methods and is often theoretically motivated by heavy-tailed gradient noise, where even second moments may be infinite, seemingly contradicting empirical risk minimization where all moments are finite for a fixed dataset. We resolve this paradox by explicitly separating data sampling from optimization randomness: although moments are finite conditional on the dataset, heavy-tailed data induce dataset-dependent noise whose second moment typically grows with the dataset size $N$. In particular, when $\|\nabla f(x_\star,\xi)\|$ has tail index $\alpha \in (1,2)$, the quantity $\frac{1}{N}\sum_{i=1}^N\|\nabla f(x_\star,\xi_i)\|^2$ scales as $N^{\frac{2}{\alpha}-1}$, leading to deteriorating convergence guarantees for standard SGD as $N$ increases. In contrast, we show that stochastic gradient descent with clipping avoids this growth and admits finite-sum convergence guarantees under heavy-tailed data for broad step-size and clipping schedules. We further derive generalization bounds for strongly convex smooth objectives and show that the tail behavior of gradients at the population minimizer is the key quantity linking optimization and generalization under heavy-tailed data.

Optimization · Non-Convex

Dmitrii Feoktistov, Andrey Veprikov, Amir Zainullin, Timofey Belinsky, Aleksandr Beznosikov

Sign-based optimization methods, such as SignSGD and Signum, have become essential for modern Deep Learning due to their 1) high performance 2) low memory footprint and 3) communication efficiency. Despite their success, these methods suffer from distinct limitations in the terminal phase of training: they decouple update mechanisms from gradient magnitudes and fail to account for parameter heterogeneity, often leading to oscillation rather than convergence. While switching to SGD represents a potential remedy, a naive "hard" switch is poorly useful due to learning rate mismatches, momentum buffer suboptimality, and the assumption of uniform parameter dynamics. In this work, we propose SoftSignum, a novel optimization method that implements a principled, smooth transition mechanism from sign-based updates to SGD, which adapts to individual parameter sensitivities. We provide a generalized theoretical framework guaranteeing convergence in stochastic non-convex settings relevant to Deep Learning and demonstrate empirically that SoftSignum effectively handles parameter heterogeneity, yielding superior convergence across diverse tasks, including LLM pretraining, compared to standard sign-based baselines.

Optimization · Stochastic

Maria-Eleni Sfyraki, Jun-Kun Wang

Stochastic Frank-Wolfe is a classical optimization method for solving constrained optimization problems. On the other hand, recent optimizers such as Lion and Muon have gained quite significant popularity in deep learning. In this work, building on recent initiatives, we provide a unifying perspective by interpreting these seemingly disparate methods through the lens of Stochastic Frank-Wolfe. Specifically, we show that Lion and Muon with weight decay can be viewed as special instances of a Stochastic Frank-Wolfe, and we establish their convergence guarantees in terms of the Frank-Wolfe gap, a standard stationarity measure in non-convex optimization for Frank-Wolfe methods. We further find that convergence to this gap implies convergence to a KKT point of the original problem under a norm constraint for Lion and Muon. Moreover, motivated by recent empirical findings that stochastic gradients in modern machine learning tasks often exhibit heavy-tailed distributions, we extend Stochastic Frank-Wolfe to settings with heavy-tailed noise by developing two robust variants with strong theoretical guarantees that hold for general compact convex sets without the need for a large batch size, filling the gap in the literature on Stochastic Frank-Wolfe for non-convex optimization. Our contributions in the later part of this work, in turn, yield new variants of Lion and Muon, that better accommodate heavy-tailed gradient noise, thereby enhancing their practical scope.

Optimization · Large Scale, Parallel and Distributed

Yijiang Li, Emon Dey, Zilinghan Li, Krishnan Raghavan, Ravi Madduri, Kibaek Kim

Federated learning~(FL) across multiple HPC facilities faces stochastic \emph{admission delays} from batch schedulers that dominate wall-clock time. Synchronous FL suffers from severe stragglers, while asynchronous FL accumulates stale updates when queues spike. We propose \fedqueue{}, a queue-aware FL protocol that incorporates scheduler delays directly into training and aggregation, which (i) predicts per-facility queue delays online to budget local work, (ii) applies cutoff-based admission that buffers late arrivals to bound staleness, and (iii) performs staleness-aware aggregation to stabilize heterogeneous local workloads. We prove the convergence for non-convex objectives at rate $\mathcal{O}(1/\sqrt{R})$ under bounded staleness, and show that the admission controls yield bounded staleness with high probability under queue-prediction error. Real-world cross-facility deployment of \fedqueue{} shows 20.5\% improvement over baseline algorithms. Controlled queue simulations demonstrate robust improvement over the baselines; in particular, about 34\% reduction in time to reach a target accuracy level under high queue variance and non-IID partitions.

Optimization · Non-Convex

Egor Shulgin, Tamaz Gadaev, Sarit Khirirat, Peter Richtarik

MARS has recently emerged as a state-of-the-art optimizer, consistently outperforming AdamW in large language model (LLM) training. It modifies the momentum-based variance reduction (MVR) update by introducing a multiplicative coefficient $\gamma$, which scales the momentum correction term. However, the existing theory of Yuan et al. (2025) does not explain why this modification improves the convergence of MARS over MVR. In this paper, we provide a rigorous theoretical explanation for the superiority of MARS over MVR. We introduce the novel similarity condition, called **$\gamma$-similarity**, which generalizes standard similarity and smoothness assumptions for analyzing stochastic algorithms. Under this condition, we derive gradient complexity guarantees for MARS, which explicitly depend on $\gamma$ and a $\gamma$-similarity constant $\delta_\gamma$. We prove that by appropriately tuning $\gamma \in [0,1]$, MARS achieves strictly lower complexity than MVR. Finally, experiments on GPT pretraining corroborate our theoretical findings, demonstrating that MARS with an optimal choice of $\gamma$ improves token efficiency over MVR, and yields substantial gains compared to AdamW.

Social Aspects · Privacy

Difei Xu, Youming Tao, Meng Ding, Chenglin Fan, Di Wang

We provide the first study of the problem of finding differentially private (DP) second-order stationary points (SOSP) in stochastic (non-convex) minimax optimization. Existing literature either focuses only on first-order stationary points for minimax problems or on SOSP for classical stochastic minimization problems. This work provides, for the first time, a unified and detailed treatment of both empirical and population risks. Specifically, we propose a purely first-order method that combines a nested gradient descent--ascent scheme with SPIDER-style variance reduction and Gaussian perturbations to ensure privacy. A key technical device is a block-wise ($q$-period) analysis that controls the accumulation of stochastic variance and privacy noise without summing over the full iteration horizon, yielding a unified treatment of both empirical-risk and population formulations. Under standard smoothness, Hessian-Lipschitzness, and strong concavity assumptions, we establish high-probability guarantees for reaching an $(\alpha,\sqrt{\rho_\Phi \alpha})$-approximate second-order stationary point with $\alpha = \mathcal{O}( (\frac{\sqrt{d}}{n\varepsilon})^{2/3})$ for empirical risk objectives and $\mathcal{O}(\frac{1}{n^{1/3}} + (\frac{\sqrt{d}}{n\varepsilon})^{1/2})$ for population objectives, matching the best known rates for private first-order stationarity.

Optimization · Non-Convex

Christopher Harker, Aditya Bhaskara

The DeepWalk algorithm has been widely used for learning node embeddings in graphs. Combined with the idea of _negative sampling_, the DeepWalk algorithm has been shown to be implementable at scale, easily handling graphs with millions of nodes. However, theoretical guarantees on the resulting embeddings are much less understood. Recent results have studied the minimizers of the objective and have shown interesting guarantees for certain graph classes. However, the optimization _trajectory_, i.e., what happens when we start at a random initialization and run gradient descent, remains poorly understood. This is especially true for the implementation of DeepWalk using Skip-gram with negative sampling (SGNS), since the variance of the stochastic updates turns out to be very large. In this work, we make progress on this question. We show that for "small norm" initialization, under a spectral gap assumption on the graph, the DeepWalk embeddings align with the column space of a fixed low-rank matrix. For graphs generated from Stochastic Block Models with certain separation conditions, our results imply that the DeepWalk embeddings recover cluster structure. To the best of our knowledge, our results give the first analysis of the optimization trajectory of DeepWalk with negative sampling on non-trivial graph classes.

Optimization · Non-Convex

Zhiyao Zhang, Myeung Suk Oh, Zhen Qin, Jiaxiang Li, Xin Zhang, Jia (Kevin) Liu

In recent years, bilevel optimization (BLO) has attracted significant attention for its broad applications in machine learning. However, most existing works on BLO remain confined to the single-task setting and rely on the lower-level strong convexity assumption, which significantly restricts their applicability to modern machine learning problems of growing complexity. In this paper, we make the first attempt to extend BLO to the multi-task setting under a relaxed lower-level general convexity (LLGC) assumption. To this end, we reformulate the multi-task bilevel learning (MTBL) problem with LLGC into an equality constrained multi-objective optimization (ECMO) problem. However, ECMO itself is a new problem that has not yet been studied in the literature. To address this gap, we first establish a new Karush–Kuhn–Tucker (KKT)-based Pareto stationarity as the convergence criterion for ECMO algorithm design. Based on this foundation, we propose a weighted Chebyshev (WC)-penalty algorithm that achieves a finite-time convergence rate of $\mathcal{O}(ST^{-\frac{1}{2}})$ to KKT-based Pareto stationarity in both deterministic and stochastic settings, where $S$ denotes the number of objectives, and $T$ is the total iterations. Moreover, by varying the preference vector over the $S$-dimensional simplex, our WC-penalty method systematically explores the Pareto front. Finally, solutions to the ECMO problem translate directly into solutions for the original MTBL problem, thereby closing the loop between these two foundational optimization frameworks.

Optimization · Stochastic

Amit Attia, Tomer Koren

The learning rate in stochastic gradient methods is a critical hyperparameter that is notoriously costly to tune via standard grid search, especially for training modern large-scale models with billions of parameters. We identify a theoretical advantage of learning rate annealing schemes that decay the learning rate to zero at a polynomial rate, such as the widely-used cosine schedule, by demonstrating their increased robustness to initial parameter misspecification due to a coarse grid search. We present an analysis in a stochastic convex optimization setup demonstrating that the convergence rate of stochastic gradient descent with annealed schedules depends *sublinearly* on the multiplicative misspecification factor $\rho$ (i.e., the grid resolution), achieving a rate of $\smash{O(\rho^{1/(2p+1)}/\sqrt{T})}$ where $p$ is the degree of polynomial decay and $T$ is the number of steps. This is in contrast to the $\smash{O(\rho/\sqrt{T})}$ rate obtained under the inverse-square-root and fixed stepsize schedules, which depend linearly on $\rho$. Experiments confirm the increased robustness compared to tuning with a fixed stepsize, that has significant implications for the computational overhead of hyperparameter search in practical training scenarios.

Reinforcement Learning · Everything Else

Mingxi Hu, Meiling Yu

Multi-objective reinforcement learning (MORL) must often support preferences that change online or are specified only after data collection. We study finite-horizon MORL with vector feedback in linear MDPs under two protocols: (i) predictable adversarial preferences revealed before each episode, and (ii) reward-free preference-free exploration (PFE), where exploration observes only transitions and must later answer arbitrary preference queries. Standard reductions are protocol-unsafe: re-scalarizing past stochastic rewards with future weights breaks the martingale structure needed for self-normalized confidence bounds, and hypervolume evaluation must account for episode-start randomization, which yields a deployable convex hull of return vectors. We propose a protocol-safe reward interface that estimates each reward coordinate via regression and performs scalarization only at query time, and we formalize deployable hypervolume semantics with a stability chain from support-function error to hypervolume error. Consequently, we obtain filtration-safe regret bounds for any predictable preference sequence without discretizing the simplex (only $\log m$ dependence) and matching near-minimax rates in linear MDPs, as well as sharp reward-free PFE guarantees: a (near-)minimax decision-optimal query answering rate $\tilde{O}(d^2 U_{\mathrm{ret}}^2/\varepsilon^2)$ and a tight separation from explicit transition-model recovery $\Theta(d(|\mathcal{S}|-1)/\varepsilon_P^2)$. These results connect online learning, preference-free deployment, and hypervolume-aware evaluation through a single protocol-aligned theory.

Theory · Learning Theory

Tal Burla, Roi Livni

We study the sample complexity of *best-case* Empirical Risk Minimizer in the setting of Stochastic Convex Optimization. We show that there exists an instance, where sample size is linear in dimension, learning is possible, but an Empirical Risk Minimizer is likely to be *unique* and *overfits*. This resolves an open question by Feldman. We also extend this to approximate ERMs. Building on our construction we also show that (constrained) Gradient Descent potentially overfits when horizon and learning rate grow w.r.t sample size. Specifically we provide a novel generalization lower bound of $\Omega\left(\eta T/(m\sqrt{m})\right)$ for Gradient Descent, where $\eta$ is the learning rate, $T$ is the horizon and $m$ is the sample size. This narrows down, exponentially, the gap between the best known upper bound of $O(\eta T/m)$ and existing lower bounds from previous constructions.

Optimization · Large Scale, Parallel and Distributed

Yihan Zhang, Xinwen Zhang, My T. Thai, Jie Wu, Hongchang Gao

Decentralized stochastic bi-level optimization has been actively studied in recent years. However, existing studies assume that the lower-level loss function is strongly convex, which limits their applicability to many machine learning models. To address this limitation, in this paper, we propose a novel decentralized stochastic first-order optimization algorithm, which does not require second-order Hessian or Jacobian matrices, for the setting where the lower-level loss function is nonconvex but satisfies the Polyak–Łojasiewicz (PL) condition. Additionally, unlike existing single-agent methods that introduce a regularization term to the lower-level loss function to artificially enforce strong convexity, our algorithm does not require such modification. Moreover, our algorithm employs a constant single-timescale learning rate for updating variables, which is different from the time-dependent and two-timescale learning rate schedules used in prior work. To establish the convergence rate, we develop a new convergence analysis framework for the pure PL condition, rather than relying on the artificial strong convexity introduced through regularization in existing single-agent methods. To the best of our knowledge, this is the first algorithm for nonconvex decentralized bi-level optimization that offers theoretical convergence guarantees under mild conditions. Finally, our extensive experimental results on hyperparameter optimization and model pruning applications validate the efficacy of the proposed algorithm.

Optimization · Stochastic

Tianxi Zhu, Yi Xu, Qi Wang, Xiangyang Ji

Recently, many empirical work has shown that, in machine learning, the noise distribution of stochastic gradients often exhibits heavy tails when stochastic optimization methods are employed. Most existing theoretical analyses of heavy-tailed stochastic methods rely on various convexity and smoothness assumptions and our knowledge of how heavy-tailed stochastic methods behave in the setting of weakly convex optimization is still limited. In the weakly convex setting, this paper derives new upper bounds on the convergence of the stochastic gradient method (SGD) under heavy-tailed noises. In particular, for vanilla SGD, we establish an in-expectation convergence guarantee on the bounded constrained domain under the assumption of bounded $p$-th central moment ($p$-BCM) of the gradient noise, and a high-probability guarantee on the unbounded domain when the noise follows a heavy-tailed sub-Weibull distribution. By equipping SGD with the gradient clipping (Clip-SGD), we demonstrate that it achieves high-probability convergence in the unbounded domain under the $p$-BCM gradient noise. All of our high-probability convergence bounds depend on the failure probability only through polynomial-logarithmic factors. Finally, we present numerical experiments to validate our theoretical findings.

Theory · Learning Theory

Yufeng Xie, Yunwen Lei

Asynchronous stochastic gradient descent (ASGD) is widely adopted in distributed and federated learning. In this paper, we develop a sharp generalization analysis for ASGD by leveraging the concept of on-average model stability. For convex and smooth objectives, we establish stability and excess risk bounds under minimal assumptions, removing Lipschitz continuity, bounded noise, bounded parameter or data domains, while allowing randomly partitioned data and arbitrary delays. Our bounds are optimistic and explicitly characterize the impact of worker participation, recovering the minimax-optimal rate $O(1/\sqrt{mn})$ in balanced regimes where $mn$ denotes the sample size and implying fast rates under low-noise conditions. We further extend the analysis to non-smooth objectives with Hölder-continuous gradients and to heterogeneous data settings via random ASGD, obtaining non-vacuous excess risk guarantees in both settings. Experimental results support our theoretical findings.

Optimization · Stochastic

Yuheng Zhao, Yu-Hu Yan, Amit Attia, Tomer Koren, Lijun Zhang, Peng Zhao

Parameter-free stochastic optimization aims to design algorithms that are agnostic to the underlying problem parameters while still achieving convergence rates competitive with optimally tuned methods. While some parameter-free methods do not require the specific values of the problem parameters, they still rely on prior knowledge, such as the lower or upper bounds of them. We refer to such methods as "partially parameter-free". In this work, we target achieving "*fully* parameter-free" methods, i.e., the algorithmic inputs do not need to satisfy any *unverifiable* condition related to the true problem parameters. We propose a general and powerful *grid search* framework, named GRASP, with a novel *self-bounding* analysis technique that effectively determines the parameter search ranges, in contrast to previous work. Our method demonstrates generality in: (i) the non-convex case, where we propose a fully parameter-free method that achieves near-optimal convergence rate, up to logarithmic factors; (ii) the convex case, where our parameter-free methods are competitive with strong performance in terms of acceleration and universality. Finally, we contribute a sharper guarantee for the model ensemble, a final step of the grid search framework, under interpolated variance characterization.

Optimization · Stochastic

Dimitris Oikonomou, Nicolas Loizou

The stochastic Polyak step size (SPS) has proven to be a promising choice for stochastic gradient descent (SGD), delivering competitive performance relative to state-of-the-art methods on smooth convex and non-convex optimization problems, including deep neural network training. However, extensions of this approach to non-smooth settings remain in their early stages, often relying on interpolation assumptions or requiring knowledge of the optimal solution. In this work, we propose a novel SPS variant, Safeguarded SPS (SPS$_{safe}$), for the stochastic subgradient method, and provide rigorous convergence guarantees for non-smooth convex optimization with no need for strong assumptions. We further incorporate momentum into the update rule, yielding equally tight theoretical results. Comprehensive experiments on convex benchmarks and deep neural networks corroborate our theory: the proposed step size achieves competitive performance to existing adaptive baselines and exhibits stable behavior across a wide range of problem settings. Finally, in the context of deep neural network training, the gradient norms under our step size do not collapse to (near) zero, indicating robustness to vanishing gradients.

Optimization · Large Scale, Parallel and Distributed

Feihu Huang, Yuning Luo, Songcan Chen

Large models recently are widely applied in machine learning, so efficient training of large models has received widespread attention. More recently, a useful Muon optimizer is specifically designed for matrix-structured parameters of large models. Although some works have begun to studying the Muon optimizer, the existing Muon and its variants still suffer from high sample complexity or high memory for large models. To fill this gap, we propose a light and fast Muon (LiMuon) optimizer for training large models, which builds on the momentum-based variance reduced technique and randomized Singular Value Decomposition (SVD). In particular, our LiMuon optimizer simultaneously has a lower memory and lower sample complexity than the Muon. Moreover, we prove that our LiMuon has a lower sample complexity of $O(\epsilon^{-3})$ for finding an $\epsilon$-stationary solution of non-convex stochastic optimization under the generalized smooth condition. Numerical experimental results on training Mamba-130M, Qwen2.5-0.5B and ViT models demonstrate effectiveness of our LiMuon optimizer.