Adaptive gradient methods are workhorses in deep learning. However, the convergence guarantees of adaptive gradient methods for nonconvex optimization have not been thoroughly studied. In this paper, we provide a fine-grained convergence analysis for a general class of adaptive gradient methods including AMSGrad, RMSPr…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “Adaptive methods”
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.
Adaptive Bayesian quadrature (ABQ) is a powerful approach to numerical integration that empirically compares favorably with Monte Carlo integration on problems of medium dimensionality (where non-adaptive quadrature is not competitive). Its key ingredient is an acquisition function that changes as a function of previou…
Adaptive gradient methods, which adopt historical gradient information to automatically adjust the learning rate, despite the nice property of fast convergence, have been observed to generalize worse than stochastic gradient descent (SGD) with momentum in training deep neural networks. This leaves how to close the gene…
Improved privacy and utility in machine learning with adaptive differential privacy.
problem Enhancing privacy in machine learning models while maintaining utility.
method Adaptive differentially private (ADP) learning method that optimally adapts noise to stepsize.
result ADP method significantly improves utility compared to standard differentially private methods.
New adaptive step-size method for convex optimization without tuning.
problem Optimizing convex functions efficiently with stochastic gradients.
method Adapted Adaptive Gradient Descent Without Descent to stochastic setting.
result Stochastic gradient descent converges under various assumptions.
This paper improves neural network generalization by dynamically learning kernel parameters.
problem Improving neural network generalization and adaptability.
method Diagonal adaptive kernel model that learns kernel eigenvalues and output coefficients during training.
result The diagonal adaptive kernel model significantly improves generalization over fixed-kernel methods.
Proposes first method for continuously indexed domain adaptation.
problem Challenges of transferring knowledge between continuously indexed domains.
method Combines adversarial adaptation with a novel discriminator.
result Outperforms state-of-the-art methods on synthetic and real-world datasets.
FLAP adapts policies quickly to new tasks using shared linear representations.
problem Adapting policies to new tasks efficiently and effectively.
method FLAP uses a shared linear representation and a separate adapter network for quick adaptation.
result FLAP achieves up to 8X faster adaptation and significantly better performance on out-of-distribution tasks.
GeoAdaLer enhances geometric understanding of Adam for stochastic optimization.
problem Understanding geometric principles behind Adam's success in stochastic optimization.
method Introduces GeoAdaLer, an adaptive learning method based on geometric properties.
result Extends interpretability and effectiveness in complex optimization scenarios.
Paper presents a Transformer model for automatic domain adaptation.
problem Challenges in selecting or designing domain adaptation algorithms.
method Transformer model approximates and selects domain adaptation algorithms.
result Transformers can approximate and automatically select domain adaptation algorithms.
Adaptive methods such as Adam and RMSProp are widely used in deep learning but are not well understood. In this paper, we seek a crisp, clean and precise characterization of their behavior in nonconvex settings. To this end, we first provide a novel view of adaptive methods as preconditioned SGD, where the precondition…
Adaptive methods improve gradient descent and proximal gradient for convex optimization.
problem Improving efficiency of gradient descent and proximal gradient methods.
method Adaptive versions of GD and ProxGD using local curvature information.
result Proved convergence with local Lipschitz gradient assumptions.
Adaptive momentum method solves non-convex min-max problems.
problem Non-convex min-max optimization problems in training generative adversarial networks.
method Proposes an adaptive momentum algorithm for non-convex min-max optimization.
result Establishes non-asymptotic convergence rates for the proposed algorithm.
Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural networks. Examples include AdaGrad, RMSProp, and Adam. We show that for simple overparameterized problems, adaptive methods often find drasti…
Local adaptive methods in FL can accelerate convergence but introduce bias, which is corrected.
problem The effect of using adaptive optimization methods for local updates in federated learning.
method Proposed correction techniques to overcome the bias introduced by local adaptive methods.
result Correction techniques can achieve faster convergence and higher test accuracy than baseline methods.
From a simplified analysis of adaptive methods, we derive AvaGrad, a new optimizer which outperforms SGD on vision tasks when its adaptability is properly tuned. We observe that the power of our method is partially explained by a decoupling of learning rate and adaptability, greatly simplifying hyperparameter search. I…
Paper analyzes nonconvex bandit problems with improved adaptive methods.
problem Continuous armed bandit problems for nonconvex cost functions.
method Simple and adaptive bin splitting methods.
result Adaptive method achieves locally minimax optimal expected cumulative regret.
Adaptive importance sampling is a class of techniques for finding good proposal distributions for importance sampling. Often the proposal distributions are standard probability distributions whose parameters are adapted based on the mismatch between the current proposal and a target distribution. In this work, we prese…
New adaptive methods solve weakly convex stochastic optimization problems.
problem Solving weakly convex stochastic optimization problems.
method Adaptive first and zeroth-order methods using exponential moving averages.
result Established non-asymptotic convergence rates for nonsmooth and nonconvex problems.
Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocolcs.LG
This paper improves domain adaptation methods using graph embedding.
problem Alleviating distribution gaps between different data domains.
method Formulate domain adaptation as graph embedding, analyze loss functions, propose rectified evaluation protocol.
result Improved benchmarks on standard datasets demonstrate the effectiveness of the proposed methods.
New model-based methods adapt pre-trained policies to unseen environments efficiently.
problem High sample complexity in reinforcement learning limits practical applications.
method Combines online learning and adaptive control to adapt policies in unseen environments.
result Proves policies can quickly recover trajectories from source to target environments.
Adaptive dropout and regularization are shown to be dual in linear networks.
problem Sparsifying deep neural networks.
method Examining dropout in the linear case, revealing a duality with regularization.
result Adaptive dropout methods lead to sparse solutions with effective penalties similar to classical sparse optimization penalties.
TiAda adapts adaptive gradient methods for nonconvex minimax optimization.
problem Nonconvex minimax optimization challenges in achieving convergence.
method TiAda is a time-scale adaptive GDA algorithm for nonconvex minimax optimization.
result TiAda achieves near-optimal complexities in deterministic and stochastic settings.
Stochastic Gradient Langevin Dynamics infuses isotropic gradient noise to SGD to help navigate pathological curvature in the loss landscape for deep networks. Isotropic nature of the noise leads to poor scaling, and adaptive methods based on higher order curvature information such as Fisher Scoring have been proposed t…
We introduce a gradient-based learning method to automatically adapt Markov chain Monte Carlo (MCMC) proposal distributions to intractable targets. We define a maximum entropy regularised objective function, referred to as generalised speed measure, which can be robustly optimised over the parameters of the proposal di…
A new adaptive splitting method improves accuracy for Cox-Ingersoll-Ross model.
problem Improving numerical solution accuracy for Cox-Ingersoll-Ross model.
method Adaptive splitting method over deterministic and random meshes, with uniform moment bound and strong error results.
result Uniform moment bound and strong error results of order 1/4 in L1 and L2 for κθ>σ^2, and order 1 for large noise.
The paper examines Adaptive Lasso and Transfer Lasso, highlighting their differences and proposing a new method.
problem Comparing and contrasting Adaptive Lasso and Transfer Lasso.
method Theoretical analysis of asymptotic properties and introduction of a new method.
result The Transfer Lasso method reduces non-asymptotic estimation errors compared to Adaptive Lasso.
Adaptive methods learn from multiple datasets, leveraging similarities and robust to outliers.
problem Simultaneously analyze multiple datasets with possible similarities and differences.
method Adaptive multi-task learning methods that automatically utilize similarities and handle differences.
result Sharp statistical guarantees and robustness against outlier tasks demonstrated.
This paper explores adaptive methods in over-parameterized linear regression.
problem Understanding why neural networks generalize well in over-parameterized settings.
method Characterizes two sub-classes of adaptive methods and their generalization performance.
result Adaptive methods in over-parameterized linear regression converge to the minimum norm solution.
Adaptive gradient methods like AdaGrad are widely used in optimizing neural networks. Yet, existing convergence guarantees for adaptive gradient methods require either convexity or smoothness, and, in the smooth setting, only guarantee convergence to a stationary point. We propose an adaptive gradient method and show t…
Calibration in Machine Learning Uncertainty Quantification: beyond consistency to target adaptivitystat.ML
New methods for better uncertainty prediction in ML.
problem Insufficient calibration in machine learning regression.
method Conditional calibration with respect to input features (adaptivity).
result Consistency and adaptivity are complementary, and good consistency does not guarantee good adaptivity.
Study shows rates for Laplacian-eigenmap methods in nonparametric regression.
problem Minimizing error in nonparametric regression using Laplacian-eigenmap.
method Adaptive and non-adaptive minimax rates using Sobolev space constraints.
result Extends minimax rates to various weighted Laplacian matrices.
Derives effective continuous dynamics for adaptive SGD methods.
problem Analyzing noise in adaptive SGD methods.
method Stochastic modified equations framework and Malladi's scaling rules.
result Sampling-induced noise in SGD limits to independent Brownian motions.
Bayesian method improves SOM training for dynamic data.
problem Training Self Organizing Maps (SOM) for non-stationary data.
method Variational Bayesian approach with adaptive neighborhood radius.
result Method outperforms other adaptive methods in high dimensions.
New method learns models to adapt to domain shifts at test time.
problem Learning models robust to distribution shifts in practical applications.
method Adaptive Risk Minimization (ARM) framework.
result Performance gains of 1-4% on image classification problems.
New method adapts without backprop, faster and better.
problem Efficient domain adaptation without source data.
method Computing class prototypes from pre-trained model.
result Significant accuracy improvements over pre-trained model.
Prototype extraction framework for domain adaptation.
problem Statistical distance minimization issues in unsupervised domain adaptation.
method Memory and computation-efficient probabilistic framework for class prototype extraction and feature alignment.
result Competitive performance with state-of-the-art methods, no additional model parameters required.
Method generates intermediate domains to align source and target domains.
problem Challenges of domain adaptation with significant domain divergence.
method Progressive domain augmentation via domain interpolation and multiple subspace alignment.
result Achieves state-of-the-art performance on multiple domain adaptation tasks.
This paper improves Adam's performance in machine learning tasks.
problem Improving the generalization ability of adaptive gradient methods.
method Develops a control theoretic framework to propose AdamSSM, a new variant of Adam.
result AdamSSM improves generalization accuracy and convergence compared to recent adaptive gradient methods.
New adaptive methods for constrained convex optimization and variational inequalities.
problem Optimization of constrained convex problems and variational inequalities.
method AdaACSA and AdaAGD+ are accelerated methods that achieve nearly-optimal convergence rates for smooth and non-smooth functions.
result Achieve nearly-optimal convergence rates for both smooth and non-smooth functions, even with stochastic gradients.
New adaptive first-order methods improve on quasi-Newton variants.
problem Designing efficient gradient methods for practical applications.
method Online scaled gradient methods (OSGM) with new adaptive methods OSGM-Best.
result OSGM-Best matches quasi-Newton variants but requires less memory and cheaper iterations.
We propose a method to construct a proposal density for the Metropolis-Hastings algorithm in Markov Chain Monte Carlo (MCMC) simulations of the GARCH model. The proposal density is constructed adaptively by using the data sampled by the MCMC metho d itself. It turns out that autocorrelations between the data generated …
Adaptive optimization methods bias neural network trajectories towards regions of lower local geometry.
problem The success of adaptive optimization methods in neural networks is not fully explained by traditional second-order methods.
method Local trajectory analysis and introduction of a new statistic .
result Adaptive methods like Adam bias trajectories towards regions of lower local geometry, leading to faster convergence.
New method for pricing options in stochastic volatility models.
problem Pricing options in models with stochastic volatility.
method Time-adaptive, high-order compact finite difference scheme.
result Extends fourth-order multistep methods to stochastic volatility models.
A new federated learning method reduces communication costs and improves adaptivity.
problem Large communication overhead and lack of adaptivity in federated learning.
method FedCAMS: A novel communication-efficient adaptive federated learning method with theoretical guarantees.
result FedCAMS achieves the same convergence rate as non-compressed federated learning methods.
AdAdaGrad optimizes batch sizes for deep learning models, reducing the generalization gap.
problem The generalization gap between large-batch and small-batch training in deep learning.
method AdAdaGrad introduces adaptive batch size strategies derived from adaptive sampling methods.
result AdAdaGradNorm converges to a first-order stationary point with a rate of O(1/K) in K iterations.
We identity a by-far-unrecognized problem of Adam-style optimizers which results from unnecessary coupling between momentum and adaptivity. The coupling leads to instability and divergence when the momentum and adaptivity parameters are mismatched. In this work, we propose a method, Laprop, which decouples momentum and…