OBD algorithm optimizes online convex optimization with strong convexity and switching costs.
problem Online convex optimization with strong convexity and switching costs.
method Online Balanced Descent (OBD) algorithm for m m m -strongly convex costs with near-optimal dynamic regret and per-round accuracy for ε ε ε -smooth sequences. result OBD achieves a competitive ratio of 3 + O ( 1 / m ) 3 + O(1/m) 3 + O ( 1/ m ) for m m m -strongly convex costs. Improved cumulative regret for sequence prediction with limited expert advice.
problem Minimizing cumulative regret in sequence prediction with limited information.
method Convex combination of experts with limited observation, achieving constant regret.
result Strategies achieve constant regret independent of the horizon T, improving over standard bounds.
New algorithm reduces online learning regret for bounded recall games.
problem Reducing regret in online learning with limited past information.
method Constructing a stationary bounded-recall algorithm with O ( 1 / M ) O(1/\sqrt{M}) O ( 1/ M ) regret. result Any low regret bounded-recall algorithm must be aware of past losses' order.
Efficient methods reduce projections in non-stationary online learning.
problem Optimizing dynamic and adaptive regret in non-stationary online learning environments.
method Presented efficient methods reducing the number of projections per round from O ( log T ) O(\log T) O ( log T ) to 1 1 1 . result Reduced number of projections per round from O ( log T ) O(\log T) O ( log T ) to 1 1 1 for optimizing dynamic and adaptive regret. FedAVOT improves federated learning by aligning user distributions.
problem Partial client participation leads to biased and unstable updates in federated learning.
method Formulates aggregation as masked optimal transport to align availability and importance distributions.
result Achieves a standard O(1/√T) rate, independent of the number of participating users per round.
New algorithms adapt to both gradient norms and comparator norms in online learning.
problem Adapting to both gradient norms and comparator norms in online learning.
method Developed parameter-free and scale-free algorithms for unbounded online convex optimization.
result Improved regret bounds for scale-invariant online prediction with linear models.
FL's early training phase significantly impacts final test accuracy.
problem Understanding how early phases affect FL's final test accuracy.
method Generalized Fisher Information Matrix (FedFIM) to FL.
result FL exhibits critical learning periods where small errors can have large impacts.
Proposes DEXP3.M for unknown delay in multi-arm bandit with multiple play.
problem Unknown delays in adversarial multi-armed bandit with multiple play.
method DEXP3.M algorithm addressing the challenge of associating feedback losses to arms.
result Regret bound is only slightly worse than single play setting.
This paper proposes a communication-efficient distributed algorithm for high-dimensional data mining.
problem Reducing communication time and rounds in distributed data mining.
method Straggler-agnostic and bandwidth-efficient distributed primal-dual algorithm.
result Guaranteed linear convergence rate for convex problems.
UCBoost improves bandit algorithms to balance optimality and complexity.
problem Finding near-optimal multi-armed bandit algorithms with low complexity.
method Boosting approach to Upper Confidence Bound (UCB) algorithms.
result UCBoost algorithms achieve near-optimal regret guarantees with significantly reduced computational complexity.
New algorithm achieves nearly optimal regret with one-pass updates for GLB problems.
problem Generalized linear bandits with non-linear reward distributions.
method Jointly efficient algorithm using OMD estimator with one-pass updates.
result Nearly optimal regret bound with O ( 1 ) \mathcal{O}(1) O ( 1 ) time and space complexities per round. Paper analyzes regret bounds for unconstrained online optimization.
problem Minimizing regret in dynamic online learning for strongly convex and smooth functions.
method Preconditioned OGD, Online Optimistic Newton (OON), multiple gradient queries.
result Achieves O ( C 2 , T ∗ ) O(C^*_{2,T}) O ( C 2 , T ∗ ) regret bound with one gradient query per round. Optimized online learning with kernels for large-scale adversarial data.
problem Efficient online learning for large-scale, potentially adversarial datasets.
method Online variations of kernel Ridge regression using approximated basis functions.
result Optimal regret for a wide range of kernels with low per-round complexity.
We consider the closely related problems of bandit convex optimization with two-point feedback, and zero-order stochastic convex optimization with two function evaluations per round. We provide a simple algorithm and analysis which is optimal for convex Lipschitz functions. This improves on \cite{dujww13}, which only p…
This paper tackles combinatorial pure exploration for dueling bandits, aiming to find the best candidate-position match.
problem Finding the best candidate-position match in a dueling bandit setting.
method The paper adapts combinatorial pure exploration for multi-armed bandits to dueling bandits, considering both Borda winner and Condorcet winner cases. It designs PAC and exact algorithms for Borda winner and a fully polynomial time approximation scheme (FPTAS) for Condorcet winner.
result The paper introduces the first algorithm with polynomial running time per round for identifying the Condorcet winner in CPE-DB.
Federated learning is vulnerable to backdoor attacks; a new defense method is proposed.
problem Backdoor attacks in federated learning that can misclassify models.
method Adjusting the learning rate based on sign information of agents' updates.
result Our defense significantly reduces or eliminates backdoor attacks in federated learning.
A new algorithm reduces the time and space complexity for multinomial logistic bandits.
problem High-dimensional feedback in multinomial logistic bandits makes existing algorithms inefficient.
method Integrates frequent directions matrix sketching into OFUL-MLogB to reduce time and space complexity.
result Achieves a regret bound of i l d e O ( Δ T ( K d ln Δ T + m ) T ) ilde{\mathcal{O}}(Δ_T(Kd\lnΔ_T+m)\sqrt{T}) i l d e O ( Δ T ( K d ln Δ T + m ) T ) . New algorithm for online portfolio selection with reduced runtime.
problem Maximizing total return in online portfolio selection.
method Minimizes current logarithmic loss regularized by log-determinant of Hessian.
result Achieves regret guarantee similar to Universal Portfolios with reduced runtime.
New research shows parallel optimization is ineffective for convex problems.
problem The inefficiency of parallel optimization methods for convex problems.
method Lower bounds analysis in the local oracle model of computation.
result Parallel and randomized algorithms cannot speed up convex optimization in various geometries and objective functions.
CyBeR-0 optimizes federated learning with Byzantine resilience and reduced communication costs.
problem Byzantine attacks and communication inefficiency in federated learning.
method Transformed robust aggregation for zero-order optimization under client heterogeneity.
result CyBeR-0 achieves stable performance with minimal communication costs and reduced memory usage.
New algorithm for nonstationary GLBs reduces computation and memory costs.
problem Nonstationary generalized linear bandits with unknown time-varying parameters.
method Discounted Online Mirror Descent (DOMD) for parameter estimation.
result Dynamic regret bounds of order O ( 1 ) O(1) O ( 1 ) per round in drifting and piecewise-stationary environments. New algorithm reduces unfairness in bandit problems by balancing exploration and exploitation.
problem Fairness in bandit problems where early participants can be unfairly disadvantaged.
method Introduces extsf{UCB-HARE} algorithm that balances exploration and exploitation using inverse-weighted harmonic rank schedule.
result Algorithm extsf{UCB-HARE} achieves regret matching the lower bound Ω ( σ k max ( 1 , q ) / T ) Ω(σ\sqrt{k^{\max(1,q)}/T}) Ω ( σ k m a x ( 1 , q ) / T ) for q > 1 q>1 q > 1 . 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.
We present efficient algorithms for the problem of contextual bandits with i.i.d. covariates, an arbitrary sequence of rewards, and an arbitrary class of policies. Our algorithm BISTRO requires d calls to the empirical risk minimization (ERM) oracle per round, where d is the number of actions. The method uses unlabeled…
New method tackles online DR-submodular maximization with improved regret guarantees.
problem Online maximization of non-monotone DR-submodular functions over down-closed convex sets.
method 1/e-linearization through exponential reparametrization, surrogate potential, and reduction to online linear optimization.
result Achieves O ( T 1 / 2 ) O(T^{1/2}) O ( T 1/2 ) static regret with single gradient query per round, improving state of the art. Algorithm identifies Pareto front in multi-objective bandits efficiently.
problem Sequentially learning the Pareto front in multi-objective bandits.
method Efficient algorithm achieving optimal sample complexity.
result Correct answer with high probability in minimal rounds.
New algorithm reduces online logistic regression regret without exponential constant.
problem Improper learning in online logistic regression with logarithmic regret.
method Regularized empirical risk minimization with surrogate losses.
result Regret scaling as O(B log(Bn)) with low computational complexity.
Paper proposes a faster federated learning method for logistic regression.
problem Federated learning for logistic regression with disjoint feature sets.
method Quasi-Newton method under additively homomorphic encryption.
result Significant reduction in communication rounds with minimal additional cost.
Improved algorithm for contextual bandits with reduced regret.
problem Adversarial contextual bandits with i.i.d. contexts.
method Oracle-efficient relaxation with O ( T 2 3 ( K log ( ∣ Π ∣ ) ) 1 3 ) O(T^{\frac{2}{3}}(K\log(|Π|))^{\frac{1}{3}}) O ( T 3 2 ( K log ( ∣Π∣ ) ) 3 1 ) regret bound. result First to improve regret bound and match original bound for stochastic case.
New algorithm offers efficient online portfolio management with logarithmic regret.
problem Online portfolio management problem, especially for large numbers of financial instruments.
method Uses Online Mirror Descent with a novel regularizer, achieving logarithmic regret.
result Achieves logarithmic regret of O(N^2(ln T)^4) with fast implementation.
Adaptive Bayesian learning aggregates experts to improve performance.
problem Bayesian online learning's performance depends on inferential choices.
method Treat Bayesian update rules as experts and aggregate them based on sequential predictive losses.
result The aggregate competes with the best expert in hindsight at a low aggregation cost.
Algorithm improves query recommendations with immediate user feedback.
problem Lack of adaptability to immediate user feedback in query recommendation algorithms.
method Augmented transformer-based causal language models with multi-armed bandit framework.
result Substantial improvement in per-round regret compared to state-of-the-art models.
The paper addresses fairness in online learning by extending auditing schemes and presenting efficient algorithms.
problem Ensuring fairness in online learning while maximizing predictive accuracy.
method Extending auditing schemes to handle multiple auditors and presenting oracle-efficient algorithms.
result Presented algorithms achieve upper bounds on regret and fairness violations, improving on existing bounds.
New method tackles high-dimensional contextual bandits with flexible kernel models.
problem Maximizing rewards in decision-making scenarios with many features.
method Introduces stochastic assumptions and no-regret learning for Gaussian kernels.
result Achieves no-regret learning even with feature dimensions growing with samples.
Technical trading rules and linear regressive models are often used by practitioners to find trends in financial data. However, these models are unsuited to find non-linearly separable patterns. We propose a decision tree forecasting model that has the flexibility to capture arbitrary patterns. To illustrate, we constr…
Paper generalizes reward distribution in multi-armed bandits with temporally-partitioned rewards.
problem Handling partial rewards distributed over multiple rounds in multi-armed bandits.
method Introduces Beta-spread property to generalize reward distribution, derives lower bound, and provides TP-UCB-FR-G algorithm.
result Improves regret upper bound for some scenarios using Beta-spread property.
New method achieves near-optimal regret without simulator.
problem Adversarial linear contextual bandits with unknown loss vectors.
method Near-optimally reduces regret to sqrt(T) without simulator.
result Achieves regret of sqrt(T) without simulator, improving existing methods.
A new algorithm improves sample complexity for thresholding in Monte Carlo Tree Search.
problem Determining if the root node value of a tree is at least a given threshold.
method Developed a δ-correct sequential sampling algorithm based on the Track-and-Stop strategy.
result Ratio-based modification of D-Tracking strategy reduces sample complexity and computational cost.
Thompson Sampling remains differentially private with minimal modifications.
problem Ensuring privacy in Thompson Sampling for multi-arm bandits.
method Demonstrated differential privacy of original Thompson Sampling, provided per-round guarantees, and introduced modifications for tighter privacy.
result Privacy guarantees can be tuned by modifying the algorithm, and these modifications impact expected regret.
New predictive bandit model with noise for better decision making.
problem Optimizing decisions with limited information and noise.
method Introduced predictive bandits, derived regret bounds, and developed algorithms.
result Developed algorithms matching theoretical regret bounds.
New algorithm reduces regret in both adversarial and stochastic contexts.
problem Contextual combinatorial semi-bandits with adversarial and corrupted stochastic regimes.
method Follow-the-Regularized-Leader (FTRL) framework with Shannon entropy regularizer, accelerated by Karush-Kuhn-Tucker conditions.
result Achieves O ~ ( T ) \widetilde{\mathcal{O}}(\sqrt{T}) O ( T ) regret in adversarial and O ~ ( ln T ) \widetilde{\mathcal{O}}(\ln T) O ( ln T ) regret in corrupted stochastic regimes. New protocol for online learning with partial feedback, extending classical methods.
problem Learning with partial feedback where only one acceptable label is observed per round.
method Introducing a collection version space to address the lack of direct extension of classical methods.
result Characterization of learnability in set-realizable regime using Partial-Feedback Littlestone dimension and Partial-Feedback Measure Shattering dimension.
We obtain the conditions for the emergence of the swarm intelligence effect in an interactive game of restless multi-armed bandit (rMAB). A player competes with multiple agents. Each bandit has a payoff that changes with a probability p c p_{c} p c per round. The agents and player choose one of three options: (1) Exploit (a …
Given a set V V V of n n n objects, an online ranking system outputs at each time step a full ranking of the set, observes a feedback of some form and suffers a loss. We study the setting in which the (adversarial) feedback is an element in V V V , and the loss is the position (0th, 1st, 2nd...) of the item in the outputted r…
Flexible algorithms for maximizing rewards in structured bandits.
problem Reward maximization in structured stochastic multi-armed bandit problems.
method Asymptotically optimal algorithms using iterative saddle-point solvers.
result Achieves optimal performance with minimal computational burden.
We consider the dynamics of player's strategies in repeated market games, where the selection of strategies is determined by a learning model. Prior theoretical analysis and experimental data show that after large number of plays the average number of agents who decide to enter, per round of the game, approaches the ma…
PRISM-FCP improves federated prediction robustness against Byzantine attacks.
problem Byzantine attacks in federated learning.
method Partial model sharing and distance-based maliciousness scores.
result Maintains nominal coverage guarantees under Byzantine attacks.
New framework handles online decisions with replenishable resources, improving both adversarial and stochastic performance.
problem Online decision-making with resource constraints that can be replenished.
method Best-of-both-worlds primal-dual template for online learning problems with replenishment.
result First positive results for adversarial inputs and an instance-independent regret bound for stochastic inputs.