A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments. Recent studies have proposed "meta" algorithms that convert any online learning algorithm to one that is adaptive to changing environments, where the adaptivity is analyzed in a quantity called the strongly-ad…
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 “Strongly Adaptive Algorithms”
This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least better, where is the time horizon. Empirical results show tha…
New online conformal prediction methods minimize strongly adaptive regret and achieve near-optimal coverage.
problem Uncertainty quantification in online settings with changing data distributions.
method Developed new online conformal prediction methods that minimize strongly adaptive regret.
result Achieve near-optimal strongly adaptive regret and approximately valid coverage.
SA algorithms control dynamic regret in non-stationary settings with strong convexity or exp-concavity.
problem Non-stationary Online Convex Optimization with dynamic regret control.
method Strongly Adaptive (SA) algorithms view dynamic regret as path variation of the comparator sequence.
result SA algorithms achieve and dynamic regret for strongly convex and exp-concave losses, respectively.
New algorithms minimize dynamic regret for strongly convex losses.
problem Minimizing dynamic regret for strongly convex losses.
method Developed Strongly Adaptive algorithms exploiting KKT conditions.
result Achieved near optimal dynamic regret of .
This paper analyzes adaptive gradient algorithms for better performance in ill-conditioned problems.
problem Poor performance of standard stochastic gradient algorithms in ill-conditioned problems.
method Non-asymptotic analysis of adaptive gradient algorithms (Adagrad and Stochastic Newton) for strongly convex objectives.
result Theoretical analysis and adaptation to practical applications like linear regression and regularized GLM.
Unintended Effects on Adaptive Learning Rate for Training Neural Network with Output Scale Changecs.LG
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.
Improved SHB method for faster convergence on strongly-convex quadratics.
problem Understanding and improving the theoretical and practical advantages of SHB.
method Noise-adaptive multi-stage algorithm for SHB with accelerated convergence.
result SHB can achieve accelerated convergence with larger mini-batch sizes.
New algorithm reduces TV-denoising to adaptive online learning.
problem Estimating TV-bounded functions from noisy samples.
method Deep connection to Strongly Adaptive online learning; time algorithm.
result Near minimax optimal rate of under squared error loss.
Introduces CSLC models to bridge deep generative models and classical algorithms.
problem Mode collapse and memorization issues in deep generative models and restrictive assumptions in classical algorithms.
method Introduces conditionally strongly log-concave (CSLC) models, factorizing data distribution into strongly log-concave conditional distributions.
result Efficient parameter estimation and sampling algorithms with theoretical guarantees for non-log-concave data distributions.
Adaptive step-size improves optimization in complex geometries.
problem Optimizing functions with non-Euclidean geometries.
method Adaptive step-size strategy for optimization algorithms.
result Guaranteed convergence for Adaptive Conditional Gradient Descent.
New algorithm tackles heterogeneous curvature in online convex optimization.
problem Adversarial bandit convex optimization with varying curvature.
method Developed an adaptive algorithm that learns curvature on the fly.
result Achieves optimal regret bounds even with heterogeneous curvature.
To deal with changing environments, a new performance measure -- adaptive regret, defined as the maximum static regret over any interval, was proposed in online learning. Under the setting of online convex optimization, several algorithms have been successfully developed to minimize the adaptive regret. However, existi…
New algorithm reduces adaptive regret without projections.
problem Computational expense of projections in online convex optimization.
method Lazy gradient-based algorithm with set-membership computations.
result Near-optimal adaptive regret bounds for general convex functions.
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.
ANIL adapts only a subset of parameters, reducing computational cost.
problem Efficiently adapt model parameters in meta-learning.
method Adapts only a small subset of parameters in the inner loop of ANIL.
result Theoretical convergence and computational complexity analysis for ANIL.
SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectivescs.LG
In this work we introduce a new optimisation method called SAGA in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates. SAGA improves on the theory behind SAG and SVRG, with better theoretical convergence rates, and has support for compos…
Adaptive personalized federated learning improves local model personalization.
problem Maximizing global model performance limits local model personalization.
method APFL algorithm trains local models while contributing to global model, with optimal mixing parameter and communication-efficient optimization.
result Demonstrates effectiveness of personalization schema and correctness of generalization theories.
We consider empirical risk minimization of linear predictors with convex loss functions. Such problems can be reformulated as convex-concave saddle point problems, and thus are well suitable for primal-dual first-order algorithms. However, primal-dual algorithms often require explicit strongly convex regularization in …
In this paper, we study adaptive online convex optimization, and aim to design a universal algorithm that achieves optimal regret bounds for multiple common types of loss functions. Existing universal methods are limited in the sense that they are optimal for only a subclass of loss functions. To address this limitatio…
Optimal online linear regression in dynamic environments using discounted Vovk-Azoury-Warmuth forecaster.
problem Achieving optimal performance in dynamic online linear regression without prior knowledge.
method Developed a discounted variant of the Vovk-Azoury-Warmuth forecaster to achieve optimal dynamic regret guarantees.
result Achieved dynamic regret of the form $O\left(d\log(T)\vee \sqrt{dP_{T}^γ(\vec{u})T}
ight)$, with a learnable discount factor.
A new algorithm reduces communication in decentralized optimization.
problem Reducing communication in decentralized optimization problems.
method Adaptive randomized communication-efficient algorithmic framework that periodically tracks disagreement error and selects influential edges for communication.
result Strong theoretical convergence guarantees and performance quantification under standard assumptions.
A Kernel Adaptive Metropolis-Hastings algorithm is introduced, for the purpose of sampling from a target distribution with strongly nonlinear support. The algorithm embeds the trajectory of the Markov chain into a reproducing kernel Hilbert space (RKHS), such that the feature space covariance of the samples informs the…
New algorithms optimize faster for simpler problems in machine learning.
problem Design faster optimization algorithms for practical machine learning problems.
method Adaptive gradient algorithms with refined conditions based on Hessian singular values.
result Achieved optimal gradient complexity for linear regression.
We consider the classical problem of sequential resource allocation where a decision maker must repeatedly divide a budget between several resources, each with diminishing returns. This can be recast as a specific stochastic optimization problem where the objective is to maximize the cumulative reward, or equivalently …
Slice Sampling has emerged as a powerful Markov Chain Monte Carlo algorithm that adapts to the characteristics of the target distribution with minimal hand-tuning. However, Slice Sampling's performance is highly sensitive to the user-specified initial length scale hyperparameter and the method generally struggles with …
Efficient algorithms for online convex optimization with limited switching decisions.
problem Online convex optimization with limited switching decisions.
method Presented computationally efficient algorithms for both general and strongly convex losses.
result Regret bounds of for general convex losses and for strongly convex losses.
Recently, much work has been done on extending the scope of online learning and incremental stochastic optimization algorithms. In this paper we contribute to this effort in two ways: First, based on a new regret decomposition and a generalization of Bregman divergences, we provide a self-contained, modular analysis of…
Learning algorithms need bias to generalize and perform better than random guessing. We examine the flexibility (expressivity) of biased algorithms. An expressive algorithm can adapt to changing training data, altering its outcome based on changes in its input. We measure expressivity by using an information-theoretic …
New method achieves both universality and adaptivity in online convex optimization.
problem Achieve optimal regret guarantees without prior knowledge of function curvature.
method Introduces UniGrad, a novel approach that achieves both universality and adaptivity.
result Achieves universal regret guarantees that adapt to gradient variation.
New algorithm reduces communication in federated learning.
problem Communication inefficiency in distributed federated learning.
method Distributionally Robust Federated Averaging (DRFA) with snapshotting scheme.
result DRFA achieves efficient convergence in various settings.
New insights show NAG and FISTA converge linearly without knowing strong convexity modulus.
problem Understanding linear convergence of NAG and FISTA without strong convexity modulus knowledge.
method High-resolution ODE framework, dynamically adapting kinetic energy coefficient.
result NAG and FISTA demonstrate linear convergence without requiring strong convexity modulus knowledge.
Two new algorithms solve nonconvex-strongly concave problems efficiently.
problem Solving nonconvex-strongly concave minimax problems.
method Proposed MINIMAX-TR and MINIMAX-TRACE algorithms.
result Find -second order stationary points within iterations.
In this paper, we consider multi-agent learning via online gradient descent in a class of games called -cocoercive games, a fairly broad class of games that admits many Nash equilibria and that properly includes unconstrained strongly monotone games. We characterize the finite-time last-iterate convergence rate for …
POCA optimizes hyperparameters with adaptive allocation for faster convergence.
problem Optimizing hyperparameters for machine learning models.
method Adaptive allocation of computational budget using Bayesian sampling.
result POCA finds strong configurations faster than its competitors.
In this paper, we propose a stochastic optimization method that adaptively controls the sample size used in the computation of gradient approximations. Unlike other variance reduction techniques that either require additional storage or the regular computation of full gradients, the proposed method reduces variance by …
Locally adaptive federated learning improves convergence in distributed machine learning.
problem Balancing local updates in federated learning leads to slow convergence.
method Locally adaptive federated learning algorithms that use uncoordinated stepsizes based on local geometric information.
result Locally adaptive methods can be particularly efficient in overparameterized settings and outperform standard federated algorithms.
New algorithm proves most inflexible manifolds are not strongly inflexible.
problem Existence of simply-connected strongly inflexible manifolds.
method Algorithm based on Sullivan models.
result One example of simply-connected inflexible manifold is not strongly inflexible.
Strongly polynomial algorithm for approximate Forster transforms and halfspace learning.
problem Computing approximate Forster transforms and halfspace learning.
method Strongly polynomial time algorithm for approximate Forster transforms and halfspace learning.
result First strongly polynomial time algorithm for distribution-free PAC learning of halfspaces.
NeAda solves nonconvex minimax optimization by balancing primal and dual variables adaptively.
problem Nonconvex minimax optimization challenges with parameter-agnostic adaptive algorithms.
method Nested Adaptive (NeAda) framework with inner and outer loops for primal and dual variables.
result Achieves near-optimal convergence rates for nonconvex-strongly-concave problems.
We derive upper and lower bounds for the policy regret of -round online learning problems with graph-structured feedback, where the adversary is nonoblivious but assumed to have a bounded memory. We obtain upper bounds of and for strongly-observable and weakly-observab…
Adaptive gradient methods have become recently very popular, in particular as they have been shown to be useful in the training of deep neural networks. In this paper we have analyzed RMSProp, originally proposed for the training of deep neural networks, in the context of online convex optimization and show -…
New proof confirms periodic orbit conjecture for Eulerisable flows.
problem Periodic orbit conjecture for non-vanishing vector fields on closed manifolds.
method Characterization of Eulerisable flows and use of strongly adapted one-forms.
result Periodic orbit conjecture holds for Eulerisable flows.
Bayesian optimization is known to be difficult to scale to high dimensions, because the acquisition step requires solving a non-convex optimization problem in the same search space. In order to scale the method and keep its benefits, we propose an algorithm (LineBO) that restricts the problem to a sequence of iterative…
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.
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…
Recursive least-squares algorithms often use forgetting factors as a heuristic to adapt to non-stationary data streams. The first contribution of this paper rigorously characterizes the effect of forgetting factors for a class of online Newton algorithms. For exp-concave and strongly convex objectives, the algorithms a…
A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraintsmath.OC
Unified analysis of first-order methods for smooth games using IQCs.
problem Certify convergence rates of first-order methods for smooth and strongly-monotone games.
method Adapted integral quadratic constraints (IQCs) to study first-order methods and derive tight upper bounds of convergence rates.
result First global convergence rate for the negative momentum method with iteration complexity.