Local SGD outperforms minibatch SGD for quadratic objectives.
problem Theoretical foundations of local SGD are lacking.
method Proved local SGD strictly dominates minibatch SGD for quadratic objectives and accelerated local SGD is minimax optimal.
result Local SGD does not dominate minibatch SGD in general convex objectives.
Minibatch SGD outperforms Local SGD in heterogeneous distributed learning.
problem Optimizing a combined convex objective with stochastic gradient estimates from different machines.
method Analysis of Minibatch SGD and Local SGD in a heterogeneous distributed setting.
result Minibatch SGD dominates Local SGD in the heterogeneous distributed setting.
Enhanced ROOT-SGD optimizes stochastic optimization with diminishing stepsizes.
problem Improving statistical efficiency in stochastic optimization.
method Integrates a diminishing stepsize strategy into ROOT-SGD.
result Achieves optimal convergence rates with improved stability and precision.
Paper shows local SGD outperforms mini-batch SGD under certain conditions.
problem Proving local SGD's superiority in distributed learning with heterogeneous data.
method New lower and upper bounds for local SGD under first-order heterogeneity assumptions.
result Local SGD is min-max optimal under certain conditions, resolving understanding of distributed optimization.
Study reveals convergence properties of SGD with random learning rate.
problem Analyzing convergence of SGD with random learning rate in non-convex optimization.
method Introduced Poisson SGD with random learning rate and used stationary distribution analysis.
result Poisson SGD converges to a stationary distribution and finds global minima in non-convex optimization.
SQuARM-SGD improves decentralized SGD efficiency with momentum.
problem Efficient decentralized training of large-scale models over networks.
method Fixed local SGD steps with Nesterov's momentum, sparsified and quantized updates, locally computed triggering criterion.
result Convergence rate matches vanilla SGD, momentum improves test performance.
Ringmaster ASGD improves Asynchronous SGD's efficiency under varying worker times.
problem Suboptimal performance of Asynchronous SGD under heterogeneous worker computation times.
method Ringmaster ASGD, a novel Asynchronous SGD method with optimal time complexity.
result Ringmaster ASGD achieves optimal time complexity under arbitrary worker heterogeneity.
Schedule-free SGD is optimal for nonconvex optimization problems.
problem Nonconvex optimization in neural networks.
method Developed a general framework for online-to-nonconvex conversion, which converts schedule-free SGD into an effective nonconvex optimization algorithm.
result Schedule-free SGD achieves optimal iteration complexity for nonsmooth, nonconvex optimization problems.
ROOT-SGD solves convex optimization problems with optimal nonasymptotic and near-optimal asymptotic performance.
problem Solving strongly convex and smooth unconstrained optimization problems using stochastic first-order algorithms.
method ROOT-SGD: Recursive One-Over-T SGD, averaging past stochastic gradients.
result Achieves state-of-the-art performance in both nonasymptotic and asymptotic senses.
We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to rescaling of weights that does not affect the output of the network, and suggest Path-SGD, which is an approximate steepest descent method with …
SGD shows distinct phases in learning single-index models, achieving optimal sample complexity and regret.
problem Learning single-index models with SGD in adaptive data settings.
method Stochastic gradient descent (SGD) with an optimal learning rate schedule.
result SGD achieves near-optimal sample complexity and regret guarantees across both burn-in and learning phases.
We consider stochastic strongly convex optimization with a complex inequality constraint. This complex inequality constraint may lead to computationally expensive projections in algorithmic iterations of the stochastic gradient descent~(SGD) methods. To reduce the computation costs pertaining to the projections, we pro…
New insights into using momentum for non-convex optimization.
problem Improving training of non-convex models like deep neural networks.
method Developed a Lyapunov analysis of SGD with momentum using stochastic primal averaging.
result Precise conditions under which SGD+M outperforms SGD and optimal hyper-parameter schedules.
Paper explores weighted averaging schemes for SGD, achieving asymptotic normality and optimality.
problem Improving convergence of SGD in various settings.
method Develops a general weighted averaging scheme for SGD and establishes asymptotic normality.
result Establishes asymptotic normality and optimality of weighted averaged SGD solutions.
MDA optimizer performs similarly to SGD+M in CV and Adam in NLP.
problem Performance degradation due to choosing the wrong optimizer.
method Modernized Dual Averaging (MDA) optimizer, inspired by dual averaging.
result MDA performs as well as SGD+M in CV and as Adam in NLP.
HybridSGD improves SGD performance by balancing computation and communication.
problem Limited scalability and performance of SGD due to communication costs.
method 2D parallel SGD method (HybridSGD) that trades off between 1D s-step SGD and 1D Federated SGD (FedAvg). result HybridSGD achieves better convergence than FedAvg at similar processor scales and up to 121x speedup over FedAvg.
Develops a parameter-free SGD algorithm with optimal convergence rate.
problem Optimizing parameters in stochastic convex optimization.
method A novel parameter-free algorithm for SGD with high-probability guarantees and adaptive properties.
result Achieves optimal convergence rate with only a double-logarithmic factor increase compared to known-parameter settings.
The Lookahead optimizer improves SGD's performance and generalization without restrictive assumptions.
problem Improving the generalization of SGD with Lookahead.
method A rigorous stability and generalization analysis of the Lookahead optimizer with minibatch SGD, leveraging on-average model stability.
result Derives generalization bounds for convex and strongly convex problems without the restrictive Lipschitzness assumption, demonstrating a linear speedup with batch size.
FSGD uses latent factors to scale SGD for high-dimensional learning.
problem Scalable optimization in high-dimensional machine learning.
method Factor-Augmented SGD (FSGD) that operates on streaming data.
result Established theoretical framework for latent factor estimation error in SGD.
SGD's performance improves with critical batch size, minimizing SFO complexity.
problem Optimizing SGD's performance with batch size and learning rate.
method Analysis of SGD using constant and decaying learning rates, focusing on batch size effects.
result SGD with critical batch size minimizes SFO complexity.
SGD converges to global minimum for certain non-convex functions.
problem Theoretical challenges in optimizing non-convex functions in machine learning.
method Perturbed SGD on a broad class of non-convex functions.
result SGD converges to global minimum for certain non-convex functions.
We propose a population-based Evolutionary Stochastic Gradient Descent (ESGD) framework for optimizing deep neural networks. ESGD combines SGD and gradient-free evolutionary algorithms as complementary algorithms in one framework in which the optimization alternates between the SGD step and evolution step to improve th…
New proof shows D-SGD and SAM are equivalent, revealing advantages of decentralization.
problem The generalization benefits of decentralized learning.
method Proved D-SGD implicitly minimizes SAM's loss function.
result Decentralized SGD and Average-direction SAM are asymptotically equivalent.
Adaptive SGD learns optimal batch size for strong convex functions.
problem Finding optimal batch size for SGD in practice.
method Adaptive SGD method that learns optimal batch size.
result Adaptive SGD exhibits nearly optimal performance in experiments.
SGD generalization bounds derived from information theory.
problem Understanding generalization of SGD for non-convex functions.
method Combining information-theoretic bounds with perturbation analysis.
result Upper bounds on SGD's generalization error based on gradient variance and function smoothness.
SGD methods fail to converge to global minimizers in deep neural networks with ReLU activation.
problem Failure of SGD methods to converge to global minimizers in deep neural networks.
method Stochastic Gradient Descent (SGD) and its variants like Adam, RMSProp, etc.
result SGD methods fail to converge to global minimizers with high probability in deep neural networks with ReLU activation.
The paper analyzes how hyperparameters affect SGD with momentum's convergence rate.
problem The role of hyperparameters in SGD with momentum's convergence rate.
method Theoretical analysis using a hyperparameters-dependent stochastic differential equation (hp-dependent SDE).
result The optimal linear rate of convergence depends on both the learning rate and the momentum coefficient.
Paper develops methods for statistical inference with SGD in nonconvex optimization.
problem Statistical inference for nonconvex optimization problems.
method Proposes two online inferential procedures combining SGD and bootstrap techniques.
result Establishes error convergence rates and asymptotically valid bootstrap confidence intervals.
Optimizes SGD for anytime neural networks, improving accuracy.
problem Training networks that produce increasingly accurate outputs over time.
method Orthogonalized SGD optimizer for nested architectures.
result Significantly improves generalization accuracy of anytime networks.
Introduces a new stochastic optimization method for deep learning.
problem Minimizing loss functions in deep neural networks.
method Introduces a second-order stochastic Runge-Kutta method and an adaptive SGD-G2.
result The method yields consistent minimization of loss functions and automatically adjusts learning rates.
AdaSGD combines SGD and Adam benefits, eliminating the need for transition.
problem Understanding when to transition from Adam to SGD for optimal performance.
method Adapting a single global learning rate for SGD (AdaSGD).
result AdaSGD combines the benefits of both SGD and Adam, improving convergence and generalization.
Paper improves learning rates for SGD and NAG.
problem Generalization performance of stochastic optimization algorithms.
method Establishes new learning rates for SGD and NAG.
result Improved guarantees in some settings or comparable rates under weaker assumptions.
RS-NSGD improves SGD convergence for heavy-tailed noise.
problem Nonconvex optimization with heavy-tailed noise.
method Integrates direction normalization into subspace updates.
result Achieves better oracle complexity than full-dimensional normalized SGD.
Improved Local SGD convergence for general convex objectives with bounded second-order heterogeneity.
problem Understanding when and why Local SGD outperforms alternatives in distributed optimization.
method Established improved convergence guarantees for Local SGD on general convex objectives under bounded second-order heterogeneity.
result Upper bounds for Local SGD are nearly tight, providing a sharper convergence theory.
Nesterov SGD is widely used for training modern neural networks and other machine learning models. Yet, its advantages over SGD have not been theoretically clarified. Indeed, as we show in our paper, both theoretically and empirically, Nesterov SGD with any parameter selection does not in general provide acceleration o…
Averaged SGD optimizes a smoothed objective, leading to better generalization.
problem Improving generalization performance in machine learning models.
method Analyzed the smoothed objective function of SGD and proved that averaged SGD can optimize this smoothed function efficiently.
result Averaged SGD can efficiently optimize a smoothed objective, leading to better generalization.
New SGD analysis for nonconvex optimization finds optimal rates.
problem Optimizing nonconvex functions in machine learning.
method Introduces a new expected smoothness assumption and analyzes SGD convergence rates.
result Optimal convergence rates for nonconvex smooth functions and global solutions under certain conditions.
New algorithms optimize without tuning, matching tuned SGD performance.
problem Optimizing machine learning models without manual hyperparameter tuning.
method Formalizes tuning-free algorithms for matching SGD performance with loose hints.
result Tuning-free algorithms can match SGD performance, but not optimal convergence rates.
Local SGD outperforms conventional methods in LLM training.
problem Training large language models on distributed devices.
method Local SGD algorithm applied to distributed training.
result Local SGD achieves competitive results in LLM training.
AdaGrad outperforms SGD in non-convex optimization problems by a factor of d.
problem Finding near-stationary points in stochastic non-convex optimization.
method Refined assumptions on smoothness and gradient noise variance, l1-norm stationarity measure. result AdaGrad achieves a convergence rate favorable over SGD in certain non-convex settings.
LAGS-SGD optimizes deep learning training by sparsifying gradients layer-wise.
problem Reduces long training times in large deep neural networks with distributed S-SGD.
method Layer-wise adaptive gradient sparsification combined with S-SGD.
result LAGS-SGD achieves convergence guarantees and outperforms vanilla S-SGD.
Random Reshuffling outperforms Stochastic Gradient Descent in smooth convex optimization.
problem Theoretical limitations of Random Reshuffling in smooth convex optimization.
method Random Reshuffling (RR) as a variant of Shuffling Stochastic Gradient Descent (Shuffling SGD).
result Random Reshuffling (RR) dominates Stochastic Gradient Descent (SGD) in smooth convex optimization under any reasonable stepsize after any finite number of epochs.
This paper improves convergence guarantees for SGD algorithms in non-convex smooth functions.
problem Theoretical convergence properties of SGD algorithms for non-convex smooth functions.
method Analysis of SGD algorithms with arbitrary data ordering for non-convex smooth functions.
result Enhanced convergence guarantees for incremental gradient and single shuffle SGD, improving the optimization term of convergence guarantee.
Private adaptive methods improve on traditional SGD for convex optimization.
problem Differential privacy constraints in gradient optimization.
method Differentially private variants of SGD and AdaGrad with adaptive stepsizes and non-isotropic clipping.
result Private AdaGrad outperforms private SGD in high-dimensional problems.
Improved time complexity for parallel stochastic optimization in heterogeneous systems.
problem Time complexity in parallel stochastic optimization for large-scale machine learning models.
method Proposes Rennala MVR, a variance-reduced extension of Rennala SGD based on momentum-based variance reduction.
result Variance reduction improves time complexity in relevant parameter regimes for parallel stochastic optimization in heterogeneous systems.
Stochastic gradient descent (SGD) is a popular stochastic optimization method in machine learning. Traditional parallel SGD algorithms, e.g., SimuParallel SGD, often require all nodes to have the same performance or to consume equal quantities of data. However, these requirements are difficult to satisfy when the paral…
Stochastic Gradient Descent (SGD) is one of the most widely used techniques for online optimization in machine learning. In this work, we accelerate SGD by adaptively learning how to sample the most useful training examples at each time step. First, we show that SGD can be used to learn the best possible sampling distr…
Iterative procedures for parameter estimation based on stochastic gradient descent allow the estimation to scale to massive data sets. However, in both theory and practice, they suffer from numerical instability. Moreover, they are statistically inefficient as estimators of the true parameter value. To address these tw…