The paper improves convergence for linear systems using entropic mirror descent with Polyak stepsizes.
problem Convergence analysis for linear systems with unbounded domain.
method Entropic mirror descent with Polyak stepsizes, sublinear and linear convergence results.
result Generalized convergence result for arbitrary convex functions.
Improved SGD methods converge faster for nonconvex optimization.
problem Nonconvex optimization challenges in machine learning.
method Adaptive SGD with line-search and Polyak stepsizes.
result Unified convergence rates for various nonconvex functions.
TD(0) with Polyak-Ruppert averaging achieves robust and fast convergence rates
problem TD(0) learning under Markovian sampling
method Polyak-Ruppert averaging with a single stepsize
result Simultaneous high-probability convergence guarantees for TD(0) iterates and PR average
New algorithms improve SGD convergence and reduce variance for over-parameterized models.
problem Slower convergence in non-interpolation settings for SGD variants.
method Proposed AdaSPS and AdaSLS with variance reduction for robust convergence.
result Achieves faster convergence rates and robustness in non-interpolation settings.
Gradient method converges locally linearly for overparameterized Gaussian mixtures.
problem Learning Gaussian mixtures under overparameterization.
method Gradient-based method alternating short descent steps and long Polyak steps.
result Gradient method converges locally linearly to minimizers.
Study on bias and extrapolation in LSA with Markovian data, showing bias reduction with Richardson-Romberg extrapolation.
problem Bias in LSA with constant stepsizes and Markovian data.
method Viewing LSA as a Markov chain, proving convergence and bias expansion, and applying Richardson-Romberg extrapolation.
result Bias is proportional to the stepsize up to higher order terms, and Richardson-Romberg extrapolation reduces the bias.
MARINA-P improves non-smooth federated optimization with adaptive stepsizes.
problem Non-smooth federated optimization in machine learning applications.
method Extends EF21-P and MARINA-P to non-smooth convex setting, proving optimal convergence rate and communication complexity bounds.
result MARINA-P achieves O ( 1 / T ) O(1/\sqrt{T}) O ( 1/ T ) convergence rate and communication complexity matching classical subgradient methods. Study on adversarial training dynamics in high dimensions using SGD.
problem Analyzing adversarial training of models in high-dimensional settings.
method Deriving deterministic equivalents for SGD iterates under Gaussian mixtures.
result No constant learning rate guarantees monotone descent in adversarial training.
FedExProx's performance is no better than GD for quadratic optimization.
problem Improving convergence of parallel proximal algorithms.
method Developed a novel analysis framework to establish tighter convergence rates.
result FedExProx can outperform GD in non-strongly convex quadratic problems.
We prove that the norm version of the adaptive stochastic gradient method (AdaGrad-Norm) achieves a linear convergence rate for a subset of either strongly convex functions or non-convex functions that satisfy the Polyak Lojasiewicz (PL) inequality. The paper introduces the notion of Restricted Uniform Inequality of Gr…
Cyclic and randomized stepsizes can lead to heavier tails in SGD, improving generalization.
problem Understanding when and why cyclic and randomized stepsizes outperform constant stepsize in SGD.
method Examined a general class of Markovian stepsizes, focusing on their tail-index behavior.
result Markovian stepsizes can achieve heavier tails, improving generalization over constant stepsize.
Study on GD and SGD over diagonal networks, focusing on stepsizes and regularisation.
problem Understanding the impact of stochasticity and large stepsizes on gradient descent and SGD solutions.
method Investigation of GD and SGD over diagonal linear networks with macroscopic stepsizes, proving convergence and characterizing solutions.
result Large stepsizes consistently benefit SGD for sparse regression problems, but can hinder GD recovery of sparse solutions, especially in the edge of stability regime.
The paper analyzes Q-learning convergence rates with asynchronous updates.
problem Analyzing convergence rates of asynchronous Q-learning algorithms.
method Derives rates of convergence using high-dimensional central limit theorems.
result Establishes a rate of order up to n − 1 / 6 log 4 ( n S A ) n^{-1/6} \log^{4} (nS A) n − 1/6 log 4 ( n S A ) for hyper-rectangles. Paper examines constant stepsize in LSA for Markovian data inference.
problem Improving statistical inference with constant stepsize in LSA for Markovian data.
method Established CLT, used averaged LSA iterates, applied Richardson-Romberg extrapolation.
result Constant stepsize leads to better CI coverage, especially with limited data.
Last SGD iterate bounds for overparameterized linear regression.
problem Analyzing the last iterate risk bounds of SGD with decaying stepsize for overparameterized linear regression.
method Problem-dependent analysis of last iterate risk bounds of SGD with geometrically decaying stepsize.
result Proved nearly matching upper and lower bounds on the excess risk for last iterate SGD with geometrically decaying stepsize.
Large stepsizes can accelerate gradient descent for logistic regression.
problem Optimizing logistic regression with large stepsizes.
method Gradient descent with large stepsize for ℓ 2 \ell_2 ℓ 2 -regularized logistic regression. result Large stepsizes can achieve O ~ ( κ ) \widetilde{\mathcal{O}}(\sqrtκ) O ( κ ) convergence, improving over O ~ ( κ ) \widetilde{\mathcal{O}}(\sqrtκ) O ( κ ) from classical theory. Large stepsize GD for logistic regression converges faster than expected.
problem Optimizing logistic regression with large step sizes.
method Gradient descent with large stepsize applied to logistic regression.
result GD converges to a lower loss in fewer steps than expected.
We revisit the classical Douglas-Rachford (DR) method for finding a zero of the sum of two maximal monotone operators. Since the practical performance of the DR method crucially depends on the stepsizes, we aim at developing an adaptive stepsize rule. To that end, we take a closer look at a linear case of the problem a…
Paper proposes a coupling-based diagnostic for SGD stepsize optimization.
problem Optimizing stepsize for SGD convergence.
method Coupling-based convergence diagnostic for monitoring stationarity.
result Proposed stepsize scheme achieves superior performance across convex and non-convex problems.
Stochastic gradient descent is the method of choice for large scale optimization of machine learning objective functions. Yet, its performance is greatly variable and heavily depends on the choice of the stepsizes. This has motivated a large body of research on adaptive stepsizes. However, there is currently a gap in o…
Improved Sparse Polyak for high-dimensional M-estimation with sparser solutions.
problem High-dimensional M-estimation problems with potential loss of sparsity and accuracy.
method Variant of Sparse Polyak with optimal thresholding operators.
result Retains desirable scaling properties while achieving sparser and more accurate solutions.
Variable metric proximal gradient (VM-PG) is a widely used class of convex optimization method. Lately, there has been a lot of research on the theoretical guarantees of VM-PG with different metric selections. However, most such metric selections are dependent on (an expensive) Hessian, or limited to scalar stepsizes l…
New algorithms eliminate stepsize tuning for bilevel optimization problems.
problem Bilevel optimization problems with unknown parameters and stepsizes.
method D-TFBO and S-TFBO algorithms with adaptive stepsizes.
result Achieve performance comparable to well-tuned approaches with theoretical guarantees.
The paper analyzes the convergence rates of Q-learning with entropy regularization and linear function approximation.
problem Analyzing the convergence rates of Q-learning with entropy regularization and linear function approximation.
method The paper derives rates of convergence using the high-dimensional central limit theorem, linearization of the soft Bellman recursion, and Gaussian approximation for the leading martingale term.
result The algorithm's last iterate satisfies high-order moment bounds, with a Gaussian approximation bound of order n − 1 / 4 n^{-1/4} n − 1/4 . New adaptive stepsize method for stochastic approximation converges to target point.
problem Finding optimal step sizes for stochastic approximation algorithms.
method Adaptive block-coordinate stepsizes using online estimates of second moment.
result New method converges almost surely to a small neighborhood of the target point.
Study on nonsmooth contractive SA with constant stepsize and Q-learning.
problem Understanding convergence and bias in nonsmooth contractive SA with different noise types.
method Proposed prelimit coupling technique for steady-state convergence and derived asymptotic bias.
result Asymptotic bias of nonsmooth SA is proportional to the square root of the stepsize.
Adaptive-stepsize MCMC sampling inspired by Adam optimizer.
problem Improving numerical stability and convergence speed in MCMC sampling.
method Time-rescaled Langevin dynamics with an auxiliary relaxation equation and adaptive stepsize control.
result Automatic stepsize control improves accuracy and stability in numerical experiments.
Formulae for Vassiliev invariants derived from Kauffman polynomial.
problem Computing Vassiliev invariants from knot polynomials.
method State model of Kauffman polynomial, Gauss diagram identities, arrow diagram identities.
result Gauss diagram formulae for Vassiliev invariants of order 3.
Sparse Polyak improves high-dimensional statistical estimation.
problem High-dimensional statistical estimation problems with growing problem dimension.
method Sparse Polyak modifies Polyak's adaptive step size to estimate restricted Lipschitz smoothness.
result Sparse Polyak achieves optimal statistical precision with fewer iterations.
Study Q-learning with constant stepsize, proving convergence and bias, and applying extrapolation.
problem Understanding and optimizing Q-learning with constant stepsize.
method Connecting Q-learning to a Markov chain, proving distributional convergence and bias, applying Richardson-Romberg extrapolation.
result Explicit expression for the linear coefficient of the asymptotic bias and improvement of RR extrapolation method.
Adaptive stepsizing improves sampling in Bayesian neural networks.
problem Scalable sampling of posterior distributions in Bayesian neural networks.
method SA-SGLD, employing time rescaling to adapt stepsize dynamically.
result SA-SGLD achieves more accurate posterior sampling than SGLD.
In smooth strongly convex optimization, knowledge of the strong convexity parameter is critical for obtaining simple methods with accelerated rates. In this work, we study a class of methods, based on Polyak steps, where this knowledge is substituted by that of the optimal value, f ∗ f_* f ∗ . We first show slightly improved …
This work analyzes Q Q Q -learning with adaptive stepsizes for finite-time convergence.
problem Finite-time convergence analysis for average-reward Q Q Q -learning with adaptive stepsizes. method Adaptive stepsizes as local clocks, time-inhomogeneous Markovian reformulation, almost-sure time-varying bounds, conditioning arguments, and Markov chain concentration inequalities.
result Convergence rates of i l d e O ( 1 / k ) ilde{\mathcal{O}}(1/k) i l d e O ( 1/ k ) for mean-square and pointwise mean-square convergence. Study Whittle index learning algorithms for restless bandits with constant stepsizes.
problem Optimizing decisions in restless multi-armed bandits with constant stepsizes.
method Developed Q-learning algorithms with constant stepsizes for index learning in restless bandits, extending to DQN and function approximations.
result The algorithms learn the Whittle index effectively.
Stochastic Gradient Descent (SGD) has played a central role in machine learning. However, it requires a carefully hand-picked stepsize for fast convergence, which is notoriously tedious and time-consuming to tune. Over the last several years, a plethora of adaptive gradient-based algorithms have emerged to ameliorate t…
Large GD stepsizes improve margins and speed up training for non-homogeneous networks.
problem Training efficiency and margin improvement in non-homogeneous two-layer networks.
method Investigation of two distinct phases in GD training, showing margin growth and empirical risk decrease.
result Large GD stepsizes lead to faster convergence and improved margins in non-homogeneous networks.
OSGM uses online learning to adapt stepsize for faster convergence.
problem Improving convergence rates of first-order methods.
method OSGM combines online learning and feedback functions to adjust stepsize.
result OSGM achieves convergence rates asymptotically no worse than optimal.
Polyak-Ruppert CLT for SA-Adam with momentum and non-convergent adaptive preconditioning
problem Adaptive optimizers combining momentum and non-convergent preconditioning
method Proving positive drift stability and a non-autonomous Polyak-Ruppert CLT for SA-Adam
result The iterate-marginal covariance is exactly the plain stochastic gradient descent (SGD) sandwich
Gradient-based temporal difference (GTD) algorithms are widely used in off-policy learning scenarios. Among them, the two time-scale TD with gradient correction (TDC) algorithm has been shown to have superior performance. In contrast to previous studies that characterized the non-asymptotic convergence rate of TDC only…
This work accelerates gradient descent with anytime convergence guarantees.
problem Improving the convergence rate of gradient descent methods.
method Proposes a stepsize schedule for gradient descent that achieves anytime convergence rates.
result Gradient descent can achieve convergence rates of O ( T − 1.119 ) O(T^{-1.119}) O ( T − 1.119 ) for any stopping time T T T . Approximate dynamic programming (ADP) has proven itself in a wide range of applications spanning large-scale transportation problems, health care, revenue management, and energy systems. The design of effective ADP algorithms has many dimensions, but one crucial factor is the stepsize rule used to update a value functi…
Gradient descent converges with arbitrary stepsize for separable data under Fenchel-Young losses.
problem Understanding the conditions under which gradient descent converges with arbitrary stepsize.
method Using Fenchel-Young losses and leveraging the classical perceptron argument to derive convergence rates.
result GD converges with arbitrary stepsize for a majority of Fenchel-Young losses, with better rates for specific loss functions.
Proposes a new adaptive gradient method based on gradient differences.
problem Manual tuning of stepsize in vanilla gradient methods.
method Adaptation driven by cumulative squared norms of gradient differences.
result More robust than AdaGrad in various settings.
The paper provides bounds for LSA with fixed stepsizes under random estimates.
problem Analyzing the performance of LSA algorithms with fixed stepsize.
method Non-asymptotic analysis based on new results about matrix moments and high probability bounds.
result Derives high probability bounds on LSA performance under weaker conditions than previous works.
Improved bounds for non-linear SA with fast convergence.
problem Stochastic approximation with non-linear mappings and multiple time scales.
method Mean squared error bounds with O ( 1 / k ) O(1/k) O ( 1/ k ) rate for contractive mappings. result First O ( 1 / k ) O(1/k) O ( 1/ k ) rate for non-linear two-time-scale SA without additional smoothness assumptions. 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.
Proposes a new adaptive learning rate for SGD.
problem Finding an efficient learning rate for SGD.
method Stochastic Polyak step-size (SPS).
result SGD with SPS converges faster for over-parameterized models.
GD with large, adaptive stepsizes achieves optimal risk in logistic regression.
problem Optimizing logistic regression with large stepsizes.
method Gradient Descent with adaptive stepsizes.
result GD achieves minimax optimal convergence in logistic regression.