New approach for distributed online optimization of non-convex losses with sublinear regret.
problem Regret evaluation and consensus in distributed, multi-agent systems with non-convex losses.
method Composite regret metric and consensus-based online normalized gradient (CONGD) approach for pseudo-convex losses; offline optimization oracle for general non-convex losses.
result First sublinear regret bound for general distributed online non-convex learning.
Paper introduces a new G ⋆ G^\star G ⋆ regret measure for online convex optimization with smooth losses.
problem Online convex optimization with smooth losses.
method Introduces a new G ⋆ G^\star G ⋆ regret measure that depends on the cumulative squared gradient norm. result The G ⋆ G^\star G ⋆ regret can be arbitrarily sharper than existing measures when losses have vanishing curvature. Balances the regret of different algorithms in bandit and RL problems.
problem Model selection in bandit and reinforcement learning.
method Estimates and balances the empirical regrets of algorithms.
result Achieves near-optimal regret compared to the optimal base algorithm.
Optimal switching regret for all segmentations in online convex optimisation.
problem Non-stationary online convex optimisation problems.
method Developed an efficient algorithm to achieve optimal switching regret on every possible segmentation.
result Achieved asymptotically optimal switching regret on every possible segmentation simultaneously.
New algorithm achieves both static and dynamic regret optimally against an oblivious adversary for deterministic losses.
problem Achieving optimal static and dynamic regret simultaneously in adversarial bandits.
method Extends impossibility result to deterministic losses, uses negative static regret and Blackwell approachability.
result First algorithm achieving optimal static and dynamic regret simultaneously against an oblivious adversary.
New algorithm reduces individual regret and communication costs in cooperative bandits.
problem Optimal individual and group regret in cooperative multi-agent bandits.
method Integrates a new communication policy into a learning algorithm.
result Achieves optimal individual regret and constant communication costs.
New algorithm CROP achieves asymptotic optimality with bounded regret.
problem Optimistic algorithms fail to achieve asymptotic instance-dependent regret optimality.
method CRush Optimism with Pessimism (CROP) algorithm that eliminates optimistic hypotheses.
result CROP achieves constant-factor asymptotic optimality and bounded regret.
Study on Pareto optimality in multi-objective bandit problems.
problem Pareto optimality in multi-objective multi-armed bandit problems.
method Formulated adversarial multi-objective multi-armed bandit, defined Pareto regrets, presented algorithms, established upper and lower bounds.
result New algorithms are optimal in adversarial settings and nearly optimal in stochastic settings.
The paper analyzes the sliding regret of stochastic bandit algorithms.
problem Measuring the one-shot behavior of no-regret algorithms in stochastic bandits.
method Introducing sliding regret to measure the worst pseudo-regret over a time-window.
result Randomized methods have optimal sliding regret, while index policies have the worst possible sliding regret.
New algorithms reduce dynamic regret in non-stationary RL environments.
problem Optimizing policies in environments that change over time.
method POWER and POWER++ algorithms for policy optimization with dynamic regret analysis.
result POWER++ improves dynamic regret by actively adapting to non-stationarity.
New algorithm reduces dynamic regret without prior function change knowledge.
problem Non-stationary stochastic optimization with bandit feedback.
method Fixed step sizes combined with multi-scale sampling framework.
result Achieves optimal dynamic regret without prior function change knowledge.
New algorithm optimizes best arm identification with minimal regret.
problem Best arm identification in multi-armed bandit problems.
method Characterized Bayesian simple regret with continuity conditions of prior, proposed a simple algorithm.
result Proposed algorithm achieves rate-optimal Bayesian simple regret.
This paper analyzes regret bounds for Gaussian process Thompson sampling.
problem Analyzing the performance of Gaussian process Thompson sampling (GP-TS) in Bayesian optimization.
method The paper derives several regret bounds for GP-TS, including a lower bound, upper bounds on the second moment of cumulative regret, expected lenient regret, and improved cumulative regret.
result The paper provides improved regret upper bounds for GP-TS, showing that it suffers from a polynomial dependence on 1 / δ 1/δ 1/ δ with probability δ δ δ . We consider regret minimization in repeated games with non-convex loss functions. Minimizing the standard notion of regret is computationally intractable. Thus, we define a natural notion of regret which permits efficient optimization and generalizes offline guarantees for convergence to an approximate local optimum. W…
Optimal algorithm found for collaborative learning in bandits with optimal regret bounds.
problem Minimizing regret in collaborative multi-agent bandit problems.
method Proposed an algorithm with optimal regret bounds for collaborative multi-agent multi-armed bandit model.
result First algorithm with order optimal regret bounds for collaborative bandit model.
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.
Efficient algorithm for global optimization of multivariate Lipschitz functions.
problem Global optimization of multivariate Lipschitz continuous functions.
method Proposes an efficient minimax optimal algorithm using a predetermined query creation rule.
result Achieves an average regret bound of O ( L n T − 1 n ) O(L\sqrt{n}T^{-\frac{1}{n}}) O ( L n T − n 1 ) , minimax optimal. The paper optimizes regret using covariance between costs and decisions.
problem Optimizing expected regret in decision-making problems.
method Developed derivative theory of covariance regret functional, derived Gâteaux derivative, and extended to constrained optimization.
result Gradient of covariance regret is the cost covariance matrix, with implications for portfolio optimization.
New algorithms minimize simple and cumulative regret in contextual bandits.
problem Minimizing simple and cumulative regret in contextual bandit settings.
method Proposed new algorithms using conformal arm sets (CASs).
result Near-optimal minimax guarantees for simple regret and state-of-the-art guarantees for cumulative regret.
In online learning, the dynamic regret metric chooses the reference (optimal) solution that may change over time, while the typical (static) regret metric assumes the reference solution to be constant over the whole time horizon. The dynamic regret metric is particularly interesting for applications such as online reco…
E 4 ^4 4 algorithm optimizes batched linear bandits with minimal regret and batches.
problem Optimizing batched linear bandits for minimal regret.
method Explore-Estimate-Eliminate-Exploit framework with optimal exploration rate.
result Achieves minimax and asymptotic optimality in regret and batch complexity.
Proposes MRO to achieve uniformly low regret in distributionally robust learning.
problem Learning under unknown test distributions (distribution shift).
method Minimax Regret Optimization (MRO) for robust machine learning.
result MRO achieves uniformly low regret across all test distributions.
New algorithm reduces regret by focusing on near-optimal actions.
problem Regret minimization in multi-armed bandits leads to over-exploitation.
method Proposes a lenient regret criterion and a new algorithm, ε-TS.
result ε-TS achieves asymptotic optimality in lenient regret.
Paper establishes no-regret property for practical EGO optimization.
problem No theoretical bounds on cumulative regret for practical EGO.
method Introduced practical EGO with a positive nugget, analyzed its regret bounds.
result Practical EGO is a no-regret algorithm with sublinear regret bounds.
Optimistic Hedge achieves optimal regret bounds in two-player zero-sum games.
problem Achieving optimal regret bounds for optimistic Hedge in two-player zero-sum games.
method Refined regret analysis and optimization problem formulation.
result Optimistic Hedge achieves O ( log m log n ) O(\sqrt{\log m \log n}) O ( log m log n ) regret bounds, matching upper and lower bounds. 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 achieves optimal regret in average reward MDPs without prior bias information.
problem Achieving optimal regret in average reward MDPs with computational efficiency and without prior bias information.
method Projective Mitigated Extended Value Iteration (PMEVI) to compute bias-constrained optimal policies efficiently.
result First tractable algorithm with minimax optimal regret of O ~ ( s p ( h ∗ ) S A T ) \widetilde{\mathrm{O}}(\sqrt{\mathrm{sp}(h^*) S A T}) O ( sp ( h ∗ ) S A T ) . Unified framework for analyzing online convex optimization across various settings.
problem Analyzing online convex optimization in different settings and feedback types.
method Unified framework allowing systematic proposal and analysis of meta-algorithms.
result Comparable regret bounds for various feedback types and adversary types.
Meta algorithm solves multivariate optimization using univariate optimizers.
problem Multivariate global optimization problems.
method Meta algorithm combining univariate global optimizers.
result Meta algorithm provides robust regret guarantees.
New DP algorithms achieve near-optimal regret bounds for online learning problems.
problem Online learning problems with zero-loss solutions and differential privacy constraints.
method Developed new Differentially Private algorithms with near-optimal regret bounds.
result Achieved near-optimal regret bounds for various online prediction and convex optimization problems.
TVBO optimizes time-varying functions with asymptotically vanishing regret.
problem Understanding the asymptotic performance of TVBO for time-varying black-box functions.
method Provided upper and lower bounds for cumulative regret of TVBO algorithms.
result TVBO algorithms can achieve asymptotically vanishing regret under certain conditions.
New algorithm reduces regret in bandit optimization for high-dimensional data.
problem Optimizing decisions in uncertain environments with high-dimensional data.
method Inspired by online Newton step, proposes a simple and efficient BCO algorithm.
result Achieves optimal regret bounds for κ κ κ -convex functions. Unified proof for various bandit algorithms with logarithmic regret.
problem Achieving logarithmic regret in stochastic bandit algorithms.
method Minimal high-probability concentration condition and two deterministic lemmas.
result Unified proofs for classical and contemporary bandit algorithms.
Optimizes quantile and semi-adversarial regret with novel root-logarithmic regularizers.
problem Minimizes regret in adversarial and semi-adversarial online learning.
method FTRL with root-logarithmic regularizers for quantile and semi-adversarial settings.
result Achieves minimax optimal regret bounds in both paradigms.
Optimized bandit algorithms have heavy-tailed regret distributions that can grow faster than expected.
problem Heavy-tailed regret distributions in optimized bandit algorithms.
method Change-of-measure ideas and UCB algorithm modifications.
result Regret distributions of optimized UCB algorithms have a heavy Cauchy tail, and can grow faster than poly-logarithmically.
Kernel-based bandit is an extensively studied black-box optimization problem, in which the objective function is assumed to live in a known reproducing kernel Hilbert space. While nearly optimal regret bounds (up to logarithmic factors) are established in the noisy setting, surprisingly, less is known about the noise-f…
The paper provides a method to minimize regret in estimate-then-optimize decision-making.
problem Errors in estimation lead to sub-optimal decisions in data-driven decision-making.
method A novel bound on regret for smooth and unconstrained optimization problems, followed by experimental design to minimize this regret.
result A general procedure for experimental design to minimize regret resulting from estimate-then-optimize.
New Thompson sampling algorithm reduces regret for exponential family bandits.
problem Minimizing regret in multi-armed bandit problems with exponential family rewards.
method Proposes ExpTS and ExpTS + ^+ + algorithms using novel sampling distributions. result Minimizes both finite-time and asymptotic regret for exponential family rewards.
Improved algorithm for adaptive dueling bandits with near-optimal regret bound.
problem Non-stationary dueling bandits with unknown number of preference changes.
method Elimination-based rescheduling algorithm for adaptive dynamic regret.
result Near-optimal i l d e O ( S e x t t t C W T ) ilde{O}(\sqrt{S^{ exttt{CW}} T}) i l d e O ( S e x ttt C W T ) dynamic regret bound. We study the problem of regret minimization for distributed bandits learning, in which M M M agents work collaboratively to minimize their total regret under the coordination of a central server. Our goal is to design communication protocols with near-optimal regret and little communication cost, which is measured by the…
The paper sets bounds on how much regret is unavoidable in adaptive LQR with unknown B-matrix.
problem Understanding the limits of adaptive LQR with unknown B-matrix.
method Local asymptotic minimax regret lower bounds using van Trees' inequality and Bellman error representation.
result Logarithmic regret is impossible if the parametrization induces an uninformative optimal policy.
We achieve a finite regret bound of O(dlogd) for online inverse linear optimization with M-convex action sets.
problem Online inverse linear optimization with M-convex action sets.
method Combining structural characterization of optimal solutions on M-convex sets with geometric volume argument.
result Finite regret bound of O(dlogd) for online inverse linear optimization with M-convex action sets.
New reinforcement learning algorithm achieves instance-optimal sample complexity.
problem Achieving low regret and identifying optimal policies in reinforcement learning.
method A novel planning-based algorithm that explicitly accounts for state visitation distributions.
result The proposed algorithm attains nearly minimax optimal sample complexity, improving over worst-case bounds.
Study nonparametric contextual bandits with batched updates, achieving optimal regret.
problem Optimal regret in nonparametric contextual bandits with batch constraints.
method Dynamic binning of covariate space, optimal regret achieved.
result Achieves optimal regret (up to logarithmic factors) for nonparametric contextual bandits.
Optimal bounds on regret and constraint violation in adversarial COCO.
problem Minimizing regret and cumulative constraint violation in adversarial COCO.
method New surrogate loss function and Follow-the-Regularized-Leader/Online Gradient Descent.
result Achieved optimal O ( T ) O(\sqrt{T}) O ( T ) bounds on both regret and cumulative constraint violation. Paper eliminates warm-up phase for PO in linear MDPs, achieving optimal regret.
problem Costly warm-up phase in PO algorithms for linear MDPs.
method Simple contraction mechanism replaces warm-up phase.
result Achieves rate-optimal regret with improved dependence on problem parameters.
Two new algorithms reduce online kernel regression's computational cost while maintaining optimal regret bounds.
problem Trade-off between regret and computational cost in online kernel regression.
method AOGD-ALD and NONS-ALD algorithms dynamically maintain nearly orthogonal basis to approximate kernel mapping and control approximate error.
result Achieves nearly optimal regret bounds at sublinear computational complexity.
Paper improves regret bounds for Gaussian process upper confidence bound in Bayesian optimization.
problem Minimizing regret in Gaussian process bandit optimization.
method Gaussian process upper confidence bound (GP-UCB) algorithm with refined analysis.
result Achieves O ( T ln 2 T ) O(\sqrt{T \ln^2 T}) O ( T ln 2 T ) cumulative regret under squared exponential kernel.