Learning-rate schedules for large models match optimization theory closely, leading to better training.
problem Improving training of large models with optimal learning rates.
method Used a bound from non-smooth convex optimization theory to match learning-rate schedules with practical benefits.
result Extending the learning-rate schedule with optimal learning-rate and transferring it across schedules improves model training.
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.
The paper analyzes how learning rate affects SGD and provides insights into optimal rates.
problem Understanding the impact of learning rate on stochastic gradient descent.
method Developed a learning-rate-dependent stochastic differential equation (lr-dependent SDE) to analyze SGD.
result Established a linear rate of convergence for SGD and found the optimal linear rate by analyzing the spectrum of the Witten-Laplacian.
Cyclical learning rate improves neural machine translation performance.
problem Optimizing learning rate for neural machine translation.
method Applied cyclical learning rate to transformer-based neural networks.
result Cyclical learning rate significantly impacts neural machine translation performance.
SALR improves deep learning generalization by dynamically adjusting learning rates.
problem Improving generalization in deep learning models.
method Sharpness-aware learning rate scheduling based on local loss function sharpness.
result SALR drives solutions to flatter regions, improving generalization and convergence.
D-Adaptation automatically sets optimal learning rates without manual tuning.
problem Optimizing learning rates for efficient convergence in machine learning.
method D-Adaptation, which asymptotically achieves optimal learning rates without back-tracking or additional evaluations.
result D-Adaptation automatically matches hand-tuned learning rates across diverse problems.
Theory extends optimal learning rates without realizability assumption.
problem Agnostic binary classification without realizability assumption.
method Identifies tetrachotomy of optimal rates and combinatorial structures.
result Optimal universal rates for binary classification in agnostic setting.
A new method automatically and dynamically sets learning rates in deep learning.
problem Determining the appropriate learning rate in deep learning tasks is challenging and often subjective.
method Local Quadratic Approximation (LQA) to automatically and dynamically set learning rates.
result The proposed method leads to nearly optimal learning rates in a computationally efficient way.
AutoGD automatically adjusts learning rates for gradient descent.
problem Optimizing learning rates for gradient descent methods.
method AutoGD automatically adjusts learning rates based on iteration.
result AutoGD can recover the optimal rate of GD for a broad class of functions.
Study examines how data augmentation impacts optimization in linear regression.
problem Understanding how data augmentation schedules affect optimization in linear regression.
method Analyzed the effect of augmentation on optimization in linear regression with MSE loss, using classical convex optimization and recent work on implicit bias.
result Proved that under certain joint schedules for learning rate and augmentation scheme, augmented gradient descent converges and characterized the resulting minimum.
VAV method optimizes learning rate for faster, stable SGD convergence.
problem Optimizing learning rate for efficient and stable machine learning models.
method Energy-based self-adaptive learning rate with auxiliary variable r. result VAV method achieves faster convergence and superior stability with larger learning rates.
New insights into optimizing Local SGD's outer optimizer for faster convergence.
problem Understanding the impact of outer optimizer and its hyperparameters in Local SGD.
method Analyzing convergence guarantees with new outer learning rates and momentum.
result Tuning the outer learning rate can improve convergence and handle inner learning rate ill-tuning.
Optimal learning rate schedules derived for various tasks.
problem Inadequate learning rate schedules in practice compared to theory.
method Refined analysis of learning rate schedules for optimization algorithms.
result Derives new problem-adaptive learning rate schedules.
Simpler, parameter-free AdaGrad and Adam variants with convergence guarantees.
problem Inefficiencies in ad-hoc learning rate tuning for optimization algorithms.
method Developed AdaGrad++ and Adam++ without predefined learning rates and proved their convergence.
result AdaGrad++ and Adam++ achieve comparable convergence rates to AdaGrad and Adam respectively.
This work analyzes the convergence rate of unrolling for optimizing quadratic objectives.
problem The challenge of accurately computing Jacobians through optimization.
method Non-asymptotic convergence-rate analysis of unrolled differentiation for gradient descent and Chebyshev method.
result There is a trade-off between fast asymptotic convergence and immediate but slower convergence due to the learning rate.
Any gradient descent optimization requires to choose a learning rate. With deeper and deeper models, tuning that learning rate can easily become tedious and does not necessarily lead to an ideal convergence. We propose a variation of the gradient descent algorithm in the which the learning rate is not fixed. Instead, w…
Unified framework for structure learning via conditional independence testing.
problem Optimal structure learning and conditional independence testing.
method Established a fundamental connection and reduction between structure learning and conditional independence testing.
result Optimal rates for structure learning are determined by conditional independence testing rates.
In this paper, we give a new sharp generalization bound of lp-MKL which is a generalized framework of multiple kernel learning (MKL) and imposes lp-mixed-norm regularization instead of l1-mixed-norm regularization. We utilize localization techniques to obtain the sharp learning rate. The bound is characterized by the d…
Analyzes optimal learning rate schedules in high-dimensional non-convex optimization problems.
problem Optimizing high-dimensional non-convex loss landscapes.
method Langevin optimization with learning rate decaying as \(η(t) = t^{-β}\).
result To speed up optimization without getting stuck in saddles, a decay rate \(β < 1\) is optimal, contrary to convex setups where \(β = 1\).
Large learning rates improve generalization, but optimal ranges are narrower than previously thought.
problem Optimizing learning rates for neural network training.
method Detailed exploration of learning rate ranges in a simplified setup, validating findings in a practical setting.
result Optimal learning rate ranges are significantly narrower than previously assumed.
Learning rate annealing improves robustness in stochastic optimization.
problem Tuning learning rates in large-scale models is costly and prone to errors.
method We analyze and demonstrate the benefits of learning rate annealing schemes.
result Stochastic gradient descent with annealed schedules converges more robustly to the optimal solution.
Optimal learning rates decay to zero in easy tasks and maintain a warmup phase in hard tasks.
problem Optimizing learning rates under functional scaling laws for model training.
method Deriving optimal learning-rate schedules based on exponents s and β. result Sharp phase transition between easy and hard tasks, with different decay behaviors.
Cyclical learning rates improve DRL performance without manual tuning.
problem Manual hyperparameter tuning in DRL is time-consuming and error-prone.
method Proposes cyclical learning rates for DRL problems.
result Cyclical learning achieves similar or better results than fixed learning rates.
Study optimizes learning rates for conditional mean embedding estimates.
problem Consistency of kernel ridge regression for conditional mean embedding.
method Adaptive statistical learning rate derived for misspecified setting.
result Upper bound matches optimal O(logn/n) rates without assuming finite dimensionality. Study problem-dependent rates in statistical learning theory, achieving optimal generalization error bounds.
problem Generalization error in statistical learning theory.
method Uniform localized convergence framework.
result Optimal generalization error bounds for various learning problems.
Optimal learning rate schedules for SGD in changing data distributions.
problem Minimizing regret in online learning with changing data distributions.
method Characterized optimal schedules for linear regression, proposed schedules for general convex and non-convex losses, and defined a notion of regret for non-convex losses.
result Upper and lower bounds for regret with constants for convex losses, and an upper bound on total expected regret for non-convex losses.
Exact risk and learning rate curves derived for adaptive SGD on high-dimensional problems.
problem Analyzing risk and learning rate dynamics in high-dimensional optimization problems.
method Developed a framework to give exact expressions for risk and learning rate curves using ODEs.
result Exact expressions for risk and learning rate curves, with detailed analysis of two adaptive learning rates.
GAIL with neural networks converges to global optima and has a known rate.
problem Uncertainty about GAIL with neural networks achieving global optimality.
method Gradient-based alternating updates algorithm.
result Established sublinear convergence to globally optimal solution.
Proof of learning rate transfer in MLPs with μP parameterization.
problem Understanding and optimizing learning rates in neural networks with different parameterizations.
method Theoretical analysis and empirical validation of learning rate transfer in MLPs with μP, SP, and NTP parameterizations. result The optimal learning rate converges to a non-zero constant as width goes to infinity under μP, explaining learning rate transfer. The paper analyzes convergence rates of bilevel optimization algorithms and introduces a new stochastic algorithm.
problem Nonconvex-strongly-convex bilevel optimization problems in machine learning.
method Comprehensive convergence rate analysis for deterministic bilevel optimization using AID and ITD, and a novel stochastic algorithm stocBiO.
result Theoretical convergence rates for AID and ITD methods, and stocBiO's superior performance.
APO optimizes neural network parameters by amortizing proximal point methods.
problem Optimizing neural network parameters online and adaptively.
method APO framework that meta-learns proximal point parameters.
result APO can recover and outperform existing optimizers and schedules.
This paper investigates the nonparametric regression problem using SVMs with anisotropic Gaussian RBF kernels. Under the assumption that the target functions are resided in certain anisotropic Besov spaces, we establish the almost optimal learning rates, more precisely, optimal up to some logarithmic factor, presented …
Unintended effects from scaling neural network outputs with adaptive learning rates.
problem Adaptive learning rate optimization's behavior is altered by output scaling, leading to misinterpretation.
method Presented a modified optimization algorithm to mitigate unintended effects.
result Adaptive learning rate's effectiveness is significantly impacted by output scaling, especially for small scaling factors.
Flexible framework for transfer learning with optimal rates.
problem Inference about a target population using related source data.
method Adaptive transfer learning framework allowing covariate-dependent relationships.
result Achieves minimax optimal rates of convergence by adapting to transfer relationship.
Random learning rate improves neural network training without extra cost.
problem Optimizing neural networks with stochastic gradient descent.
method Uniformly-distributed random learning rate in SGD.
result Random learning rate yields better regularization without extra computational cost.
GALA adapts learning rates online by aligning gradients, improving deep learning model performance.
problem Fine-tuning learning rates for deep learning models requires extensive grid search.
method GALA dynamically adjusts learning rates by tracking gradient alignment and local curvature.
result GALA produces a flexible, adaptive learning rate schedule that increases when gradients align.
WSqD extends learning rate schedules for large model training without fixed horizons.
problem Fixed learning rate schedules limit training horizon extension.
method WSqD replaces constant stable phase with a shifted inverse-square-root base, retaining linear cooldown.
result WSqD achieves minimax-optimal convergence rate and horizon-independence.
Large learning rates lead to various implicit biases in nonconvex optimization.
problem Understanding the conditions under which large learning rates yield edge of stability, balancing, and catapult phenomena.
method Developed a global convergence theory for nonconvex functions without globally Lipschitz continuous gradient, focusing on functions with good regularity.
result These implicit biases are more likely to occur in functions with good regularity, and large learning rates favor flatter regions.
Fractal learning rate schedules accelerate vanilla gradient descent.
problem Difficulty in tuning learning rates in iterative optimization.
method Introduce Chebyshev learning rate schedule for gradient descent.
result Locally unstable updates can lead to convergence in deep learning.
A new method for optimizing non-decomposable metrics with constraints.
problem Optimizing complex machine learning objectives with thresholded constraints.
method Formulate rate-constrained optimization using the Implicit Function theorem and solve with gradient-based methods.
result Demonstrated effectiveness over existing methods on benchmark datasets.
Deep learning methods achieve state-of-the-art performance in many application scenarios. Yet, these methods require a significant amount of hyperparameters tuning in order to achieve the best results. In particular, tuning the learning rates in the stochastic optimization process is still one of the main bottlenecks. …
We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in practice. We demonstrate the effectiveness of the method in a range of optimization problems by applying it to stochastic gradient descent, stochastic gradient descent with Nesterov …
Paper optimizes multi-fidelity function with fast learning rates.
problem Optimizing a locally smooth function with limited budget and varying fidelity approximations.
method Kometo algorithm that achieves simple regret rates without knowing function smoothness or fidelity assumptions.
result Kometo algorithm outperforms previous methods empirically.
The paper analyzes and improves the learning rates of distributed kernel ridge regression.
problem Generalization performance and learning rates of distributed kernel ridge regression.
method The paper derives optimal learning rates for DKRR in expectation and probability, proposes a communication strategy to improve learning performance, and evaluates these through theory and experiments.
result The communication strategy significantly improves the learning performance of DKRR, as demonstrated by both theoretical assessments and numerical experiments.
Stochastic Gradient Descent shows directional bias with moderate learning rates, impacting optimization outcomes.
problem Understanding the bias of SGD with moderate learning rates in practical scenarios.
method Analyzing SGD and GD on an overparameterized linear regression problem.
result SGD converges along large eigenvalue directions, GD along small ones, affecting early stopping outcomes.
Paper explores rate-preserving reductions between Blackwell approachability and no-regret learning.
problem Tackles rate-preserving reductions between Blackwell approachability and no-regret learning.
method Studies fine-grained reductions and optimal rates of convergence.
result Shows that rate-preserving reductions do not always hold, but provides conditions for when they do.
Optimizing deep neural networks is largely thought to be an empirical process, requiring manual tuning of several hyper-parameters, such as learning rate, weight decay, and dropout rate. Arguably, the learning rate is the most important of these to tune, and this has gained more attention in recent works. In this paper…
We focus on the problem of minimizing a convex function f over a convex set S given T queries to a stochastic first order oracle. We argue that the complexity of convex minimization is only determined by the rate of growth of the function around its minimizer xf,S∗, as quantified by a Tsybakov-like noise co…