New algorithms identify Pareto optimal sets in multi-objective bandit problems.
problem Identifying Pareto optimal sets in multi-objective bandit problems.
method Empirical Gap Elimination (EGE) algorithms combining hardness estimation and elimination schemes.
result Two EGE algorithms have exponentially decaying error probabilities with budget.
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.
In this paper, we study the stochastic version of the one-sided full information bandit problem, where we have K arms [K]={1,2,…,K}, and playing arm i would gain reward from an unknown distribution for arm i while obtaining reward feedback for all arms j≥i. One-sided full information bandit ca…
Study quantile multi-armed bandits for identifying the best arm with a specified quantile level.
problem Identifying the arm with the highest quantile in multi-armed bandits with private rewards.
method Proposed a (non-private) and differentially private successive elimination algorithms for best-arm identification.
result The proposed algorithms are essentially optimal for quantile bandit problems, with finite sample complexity even for distributions with infinite support-size.
Background: Deep learning models are typically trained using stochastic gradient descent or one of its variants. These methods update the weights using their gradient, estimated from a small fraction of the training data. It has been observed that when using large batch sizes there is a persistent degradation in genera…
The paper tackles best arm identification in contaminated bandits with optimal error guarantees and sample complexity.
problem Best arm identification in stochastic bandits with adversarial reward contamination.
method Proposes two algorithms: a gap-based algorithm and a successive elimination-based algorithm for sub-Gaussian bandits.
result Asymptotically optimal sample complexity for both algorithms.
Unified framework for CO problems using RL, providing optimal solutions and convergence guarantees.
problem Combinatorial optimization problems
method Unified framework of Markov decision processes (MDPs) and value-based reinforcement learning (RL) techniques
result RL techniques converge to approximate solutions with a guarantee on optimality gap
We present a new strategy for gap estimation in randomized algorithms for multiarmed bandits and combine it with the EXP3++ algorithm of Seldin and Slivkins (2014). In the stochastic regime the strategy reduces dependence of regret on a time horizon from (lnt)3 to (lnt)2 and eliminates an additive factor of o…
Algorithm identifies best item from subsets with random utility model feedback.
problem PAC learning the best item from subsets with random utility model feedback.
method Pairwise relative counts and hierarchical elimination for learning algorithm.
result Near-optimal PAC sample complexity guarantee for identifying ε-optimal item.
Aims to eliminate domain bias in authentication without domain labels.
problem Authentication models are biased due to domain differences.
method Discover latent domains and eliminate domain difference alternately, using a meta-learning framework.
result Eliminates domain difference in authentication without domain labels.
Balances and eliminates base algorithms in bandits and RL to bound total regret.
problem Model selection in bandits and reinforcement learning with unknown optimal regret.
method Balances and eliminates base algorithms based on candidate regret bounds.
result Total regret bound is the best valid candidate regret bound times a small multiplicative factor.
New empirical PAC-Bayes bound for Markov chains with finite state space.
problem Lack of empirical bounds for Markov chains with temporal dependence.
method Proved a new PAC-Bayes bound for Markov chains, providing an empirical pseudo-spectral gap.
result First fully empirical PAC-Bayes bound for Markov chains with finite state space.
DGKIP extends KIP for dataset distillation without bi-level optimization.
problem Efficiently distill datasets for various loss functions.
method Leverages duality theory to avoid bi-level optimization.
result DGKIP supports a wider range of loss functions.
BestChanID identifies the channel with maximal capacity using training sequences.
problem Identifying the channel with maximal capacity among several discrete memoryless channels.
method Formulated as a multi-armed bandit problem, proposed a capacity estimator, and developed gap-elimination algorithms.
result Guaranteed to output the DMC with the largest capacity with a desired confidence.
This paper studies the problem of adaptively sampling from K distributions (arms) in order to identify the largest gap between any two adjacent means. We call this the MaxGap-bandit problem. This problem arises naturally in approximate ranking, noisy sorting, outlier detection, and top-arm identification in bandits. Th…
Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios. However, recent studies show that they often lead to worse generalization performance than SGD, especially for training deep neural networks (DNNs). In this wo…
We present a provably optimal differentially private algorithm for the stochastic multi-arm bandit problem, as opposed to the private analogue of the UCB-algorithm [Mishra and Thakurta, 2015; Tossou and Dimitrakakis, 2016] which doesn't meet the recently discovered lower-bound of Ω(εKlog(T)) [Shar…
New algorithm closes empirical gap in PFSGD performance.
problem Empirical performance gap between tuned SGD and PFSGD.
method Parameter-free algorithm based on Coin-Betting ODE updates.
result New algorithm outperforms tuned baselines and matches optimal performance.
Improves Bayesian predictive performance in misspecified models.
problem Misspecification gap between inferential and predictive risks.
method Develops a multi-sample loss (PACm) to bridge the gap. result Empirical study shows improved predictive distribution.
The paper explains what affects the generalization gap in visual RL with and without distractors.
problem Understanding what affects the generalization gap in visual reinforcement learning.
method Theoretical analysis and empirical evidence.
result Minimizing representation distance between training and testing environments reduces the generalization gap.
A modern aircraft may require on the order of thousands of custom shims to fill gaps between structural components in the airframe that arise due to manufacturing tolerances adding up across large structures. These shims are necessary to eliminate gaps, maintain structural performance, and minimize pull-down forces req…
New integration method improves BSDE-based PDE solvers.
problem Discretization bias in standard BSDE-based solvers.
method Proposed Stratonovich-based BSDE formulation with stochastic Heun integration.
result Eliminates bias issues and outperforms EM-based variants.
Robust algorithm optimizes corrupted Gaussian process bandits.
problem Sequential optimization of corrupted, expensive reward functions.
method Robust GP Phased Elimination (RGP-PE) algorithm.
result Algorithm balances robustness to corruptions with exploration and exploitation.
Algorithm identifies best arm in bandit game with variance consideration.
problem Identifying the best arm in a stochastic multi-armed bandit game with varying variances.
method Adaptive algorithm using grouped median elimination to explore gaps and variances.
result Guarantees to output the best arm with probability (1-δ) using optimal number of samples.
New framework tightens certified robustness gaps in machine learning models.
problem Persistent gap between theoretical certified robustness and empirical accuracy.
method Leverages Lipschitz continuity and novel confidence intervals.
result Improves robust accuracy, compressing the gap between theory and practice.
Truncated SGD with heavy-tailed noise eliminates sharp local minima.
problem Avoiding sharp local minima in deep learning models.
method Truncated SGD with heavy-tailed gradient noise.
result Truncated SGD can eliminate sharp local minima entirely from its training trajectory.
Optimal privacy-preserving algorithm for solving saddle point problems.
problem Solving convex-concave stochastic saddle point problems under differential privacy constraints.
method Recursive regularization technique repurposed for saddle point problems, achieving strong gap rate of O(1/√n + √d/nε).
result Achieves nearly optimal strong gap rate of O(1/√n + √d/nε) with gradient complexity O(min{n^2ε^(1.5)/√d, n^(3/2)}).
Paper addresses fault-tolerance in distributed machine learning with stochastic gradient descent.
problem Fault-tolerance in distributed stochastic gradient descent (D-SGD) for machine learning.
method Proposes norm-based comparative gradient elimination (CGE) to robustify D-SGD against Byzantine faulty agents.
result CGE guarantees fault-tolerance against a bounded fraction of Byzantine agents under standard stochastic assumptions.
No semistability found for Calabi-Yau metrics near cones.
problem Understanding the stability of Calabi-Yau metrics near cones.
method Developed a 2-step degeneration theory to eliminate intermediate K-semistable cones.
result No intermediate K-semistable cone possible for Calabi-Yau metrics near cones.
New asymptotic e-values improve inference by eliminating data-dependent scaling inefficiency.
problem Data-dependent scaling inefficiency in existing asymptotic e-values.
method Drawing on Bentkus's near-optimal concentration inequalities, introduce Bentkus-type asymptotic e-values.
result Bentkus-type asymptotic e-values consistently deliver sharper inference than existing alternatives.
Proposes a flexible tournament design combining knockout and round-robin.
problem Designing a tournament that eliminates participants linearly.
method Combines knockout and round-robin structures for flexible elimination.
result Flexible tournament design can eliminate participants linearly.
Improved elimination strategies for adaptive bandit identification reduce sample complexity and computational burden.
problem Inefficient elimination strategies in bandit identification.
method Adaptive elimination methods that update sampling rules frequently and reduce problem size.
result Adaptive elimination methods achieve better sample complexity and computational efficiency.
Extracurricular learning closes the accuracy gap in knowledge distillation.
problem Accuracy gap between teacher and student models after knowledge distillation.
method Modeling student and teacher output distributions, sampling from an extended data distribution, and matching over this set.
result Extracurricular learning reduces the accuracy gap by 46% to 68%.
Improved sample complexity for diffusion models without needing empirical risk minimizers.
problem Theoretical limitations in sample complexity for diffusion models.
method Structured decomposition of score estimation error, eliminating dependence on neural network parameters.
result Achieved sample complexity bound of O(ε^(-4)) without empirical risk minimizer access.
Improves early stopping in deep networks by adjusting stepsizes.
problem Epoch-wise double descent in deep networks.
method Analytical and empirical study of bias-variance tradeoffs in different network layers.
result Eliminating epoch-wise double descent through adjusting stepsizes of different layers improves early stopping performance.
Classification may not be reliable for several reasons: noise in the data, insufficient input information, overlapping distributions and sharp definition of classes. Faced with several possibilities neural network may in such cases still be useful if instead of a classification elimination of improbable classes is done…
A new method simulates a lazy version of a Markov chain for empirical inference.
problem Estimating and testing unknown Markov chains with limited data.
method Simulates an α-lazy version of an unknown Markov chain, making it ergodic.
result The pseudo spectral gap can be applied to non-ergodic Markov chains.
New algorithm for non-stationary bandits with slow drifts.
problem Minimizing dynamic regret in non-stationary bandits with slowly varying rewards.
method Extends Successive Elimination to non-stationary bandits with a novel gap profile characterization.
result First instance-dependent regret upper bound for slowly varying non-stationary bandits.
(Unsupervised) Domain Adaptation (DA) seeks for classifying target instances when solely provided with source labeled and target unlabeled examples for training. Learning domain-invariant features helps to achieve this goal, whereas it underpins unlabeled samples drawn from a single or multiple explicit target domains …
The study finds that firm membership in flagship indices and TCFD endorsement are strong predictors of a wider Disclosure-Performance Gap.
problem The Aggregate Confusion hypothesis and the measurement of greenwashing in environmental disclosures.
method The study uses a Disclosure-Performance Gap (DPG) model to measure the divergence between voluntary environmental disclosures and realised emissions performance for 200 large European firms. The model selection process involved multiple stages and robust standard errors.
result Firm membership in flagship indices and TCFD endorsement are strong predictors of a wider gap, while renewable energy use and environmental capital expenditure significantly narrow the gap.
A new variable importance measure for DRFs detects broader impacts on output distributions.
problem Estimating full conditional distributions of multivariate outputs given inputs.
method Based on the drop and relearn principle and MMD distance.
result Consistent and high-performing variable importance measure for DRFs.
New bound limits generalization gap for large models, independent of model complexity.
problem Understanding generalization gap in large-scale machine learning models.
method Established a model-independent upper bound for generalization gap using Rényi entropy.
result Generalization gap can be maintained with arbitrarily large models if data entropy is sufficient.
A framework for modular training of robust generative models.
problem Training large generative models is resource-intensive and requires heuristic tuning.
method Modular training using a gating mechanism and a minimax game to find a robust gate.
result The modular approach can theoretically outperform monolithic baselines and is scalable.
Paper tackles treatment leakage in text-based causal inference, proposing methods to mitigate bias.
problem Treatment leakage in text-as-confounder applications introduces bias in causal estimates.
method Formal definitions, four text distillation methods (passage removal, classification, salient feature removal, nullspace projection).
result Moderate distillation optimally balances bias reduction against confounder retention.
New algorithm eliminates arms to minimize regret in complex bandit problems.
problem Minimizing regret in combinatorial bandit problems with explicit exploration.
method Introduces a novel arm elimination scheme that partitions arms into three categories and incorporates explicit exploration.
result Achieves near-optimal regret in combinatorial multi-armed and linear contextual bandit problems.
We develop a coreset for robust geometric median, reducing size dependency on outliers.
problem Robust geometric median problem in Euclidean space with outliers.
method Construction of a compact coreset with size dependency on m eliminated. result Elimination of O(m) dependency in coreset size, achieving O(ε−2⋅min{ε−2,d}) size. Algorithm reduces regret in multi-player bandits with unknown collision rewards.
problem Reducing regret in multi-player multi-armed bandits with unknown collision rewards.
method Proposes an algorithm that combines a modified successive elimination strategy with a communication protocol to estimate suboptimality gaps and coordinate among players.
result Achieves logarithmic regret for the problem when collision reward is unknown.
TimeBridge addresses non-stationarity in long-term time series forecasting.
problem Non-stationarity in multivariate time series leads to spurious regressions and obscures long-term relationships.
method TimeBridge segments series into patches, applying Integrated Attention for short-term non-stationarity and Cointegrated Attention for long-term cointegration.
result TimeBridge achieves state-of-the-art performance in both short-term and long-term forecasting.