Algorithm improves online learning in adversarial bandits.
problem Online learning in adversarial multi-armed bandits with non-uniform best arm distribution.
method Online-within-online setup, inner and outer learners, leveraging non-uniform empirical distribution of best arms.
result Improves regret bounds for non-uniform best arm distributions.
Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the standard definition of regret becomes inadequate if the adversary is allowed to a…
New insights link no-regret learning to online conformal prediction in adversarial settings.
problem Understanding the relationship between no-regret learning and online conformal prediction in adversarial environments.
method Analysis of existing algorithms and new connections between no-regret learning and conformal prediction.
result No-regret learning algorithms can provide group-conditional coverage guarantees in adversarial settings.
We present and study models of adversarial online learning where the feedback observed by the learner is noisy, and the feedback is either full information feedback or bandit feedback. Specifically, we consider binary losses xored with the noise, which is a Bernoulli random variable. We consider both a constant noise r…
Continuous-time algorithms improve online learning performance.
problem Online learning with sequential data and minimizing overall regret.
method Extending discrete-time algorithms to continuous-time models for online linear optimization, adversarial bandit, and adversarial linear bandit.
result Optimal regret bounds are proven for continuous-time settings.
New algorithm achieves logarithmic regret for adversarial online control.
problem Online linear-quadratic control in systems with adversarial disturbances.
method Characterization of optimal offline control law, reduced to online learning with approximate advantage functions.
result First algorithm with logarithmic regret for arbitrary adversarial disturbance sequences.
Bayesian algorithms improve online learning with adversaries over infinite action spaces.
problem Online learning with adversaries over infinite action spaces.
method Developed a Thompson sampling algorithm for online learning with an adversary's prior over the space of actions.
result Thompson sampling over a Gaussian process prior achieves a rate of O ( β T d log ( 1 + d λ β ) ) O(β\sqrt{Td\log(1+\sqrt{d}\fracλβ)}) O ( β T d log ( 1 + d β λ ) ) against a β β β -bounded λ λ λ -Lipschitz adversary. Oracle-efficient algorithms for online learning with smoothed and hint-adversaries.
problem Online learning with beyond worst-case adversaries.
method Oracle-efficient algorithms for two settings: smoothed analysis and K K K -hint transductive learning. result Oracle-efficient regret bounds for learning real-valued and binary-valued functions.
Extends quantum learning theory to multiclass and online settings.
problem Quantum learning theory for batch and online learning.
method Adapts classical models to quantum settings, introduces new online learning model.
result Quantum and classical sample complexities have the same form for various learning scenarios.
New framework for understanding adversarial and stochastic learning.
problem Understanding the continuum from adversarial to stochastic settings in online learning.
method Distributionally constrained adversaries framework.
result Characterization of learnable distribution classes for various function classes.
We describe an approximate dynamic programming (ADP) approach to compute approximations of the optimal strategies and of the minimal losses that can be guaranteed in discounted repeated games with vector-valued losses. Such games prominently arise in the analysis of regret in repeated decision-making in adversarial env…
Adversarial online nonparametric regression achieves optimal rates with locally adaptive learning.
problem Adversarial online nonparametric regression with general convex losses.
method Parameter-free learning algorithm leveraging chaining trees to compete against H{ö}lder functions, dynamically tracking and adapting to local smoothness variations.
result First computationally efficient algorithm with locally adaptive optimal rates for online regression in an adversarial setting.
Banker-OMD improves online learning with delayed feedback.
problem Handling delayed feedback in online learning.
method Generalized Online Mirror Descent (OMD) framework.
result Achieves nearly-optimal performance in three bandit scenarios.
The paper improves smoothed analysis for online problems with adaptive adversaries.
problem Online prediction, discrepancy minimization, and online optimization with adaptive adversaries.
method General technique to prove smoothed guarantees against adaptive adversaries, reducing to simpler oblivious adversaries.
result Strong smoothed guarantees for three online problems, matching or improving previous results.
Improved online convex optimization bounds between stochastic and adversarial settings.
problem Understanding optimization tasks that are neither i.i.d. nor fully adversarial.
method Establishing novel regret bounds exploiting smoothness of expected losses.
result Regret bounds improve on previous results by reducing dependence on maximum gradient length to variance of gradients.
New bounds for online convex optimization between stochastic and adversarial settings.
problem Understanding optimization tasks that are neither i.i.d. nor fully adversarial.
method Establishing novel regret bounds exploiting smoothness of expected losses.
result Regret bounds match expected rates in the fully i.i.d. case and gracefully deteriorate in the fully adversarial case.
Proposes online conformal prediction method with adversarial semi-bandit feedback.
problem Online uncertainty quantification with adversarial semi-bandit feedback.
method Formulates online conformal prediction as an adversarial bandit problem and uses regret minimization.
result Achieves long-run coverage guarantee with adversarial semi-bandit feedback.
New algorithms achieve no-regret learning even with adversarial transitions and losses.
problem No-regret learning impossible with adversarial transitions and losses.
method Developed algorithms for adversarial Markov Decision Processes with smooth regret increase.
result Achieved O ~ ( T + C e x t s f P ) \widetilde{O}(\sqrt{T} + C^{ extsf{P}}) O ( T + C e x t s f P ) regret, with C e x t s f P C^{ extsf{P}} C e x t s f P measuring adversarial transition function. Paper tackles online allocation problems using adversarial training.
problem Online bipartite matching, especially in AdWords.
method Constructs a framework combining game theory, adversarial training, and GANs.
result Designs robust algorithms that perform well under practical and adversarial conditions.
Study robust online learning with adversarial perturbations.
problem Learning robust classifiers in the presence of adversarial perturbations.
method Formulated as an online learning problem, considered both realizable and agnostic learnability, defined new dimension controlling mistake/regret bounds.
result Showed new dimension controls mistake/regret bounds, generalized to multiclass hypothesis classes.
ABoB optimizes online configuration tuning by clustering parameters and accelerating learning.
problem Online optimization in large, dynamic parameter spaces.
method Hierarchical adversarial bandit framework.
result Significant performance gains in adversarial metric scenarios.
New algorithm reduces regret in online learning for piecewise continuous functions.
problem Exponential loss in efficiency when moving from classical to adversarial learning.
method Introduces generalized bracketing numbers and Follow-the-Perturbed-Leader algorithm.
result Optimal scaling of optimization oracle calls with average regret.
Meta-learning improves performance across similar tasks in adversarial bandit settings.
problem Improving performance across multiple similar tasks in adversarial bandit scenarios.
method Designing meta-algorithms that combine outer learners to tune hyperparameters of inner learners for MAB and BLO.
result Meta-algorithms improve task-averaged regret for MAB and BLO, showing direct relationship with action space-dependent measures.
Algorithm learns expert weights to minimize regret in adversarial setting.
problem Learning to aggregate expert forecasts with no-regret guarantee in adversarial conditions.
method Online mirror descent algorithm for logarithmic pooling of expert forecasts.
result Achieves O ( T log T ) O(\sqrt{T} \log T) O ( T log T ) expected regret compared to best weights. Learning theory has largely focused on two main learning scenarios. The first is the classical statistical setting where instances are drawn i.i.d. from a fixed distribution and the second scenario is the online learning, completely adversarial scenario where adversary at every time step picks the worst instance to pro…
Algorithm for online decision making with unknown dynamics and aggregate feedback.
problem Online decision making with unknown dynamics and aggregate bandit feedback.
method Developed an algorithm based on online mirror descent with a self-concordant barrier regularization and an increasing learning rate schedule.
result Achieved O ( K ) O(\sqrt{K}) O ( K ) regret for the online Markov Decision Process with K K K episodes. New algorithms improve online prediction from experts with privacy constraints.
problem Online prediction from experts under privacy constraints.
method Proposed and analyzed new algorithms for approximate and pure differential privacy.
result Achieved improved regret bounds for various adversaries.
Paper proposes a new method to select memory data for online class-incremental learning.
problem Selecting which buffered images to replay for online class-incremental learning.
method Adversarial Shapley value scoring method to preserve latent decision boundaries.
result Proposed ASER method provides competitive or improved performance compared to state-of-the-art methods.
New approach for online learning with adaptive adversaries, simpler and more effective.
problem Online learning with adaptive adversaries, especially in bandits and MDPs.
method Uses standard unbiased estimators and a simple increasing learning rate schedule, aided by logarithmically homogeneous self-concordant barriers and strengthened Freedman's inequality.
result First high-probability regret bounds for adversarial bandits and MDPs, resolving open problems.
Improved learning algorithms with privacy using smoothed analysis.
problem Designing robust and private learning algorithms.
method Smoothed analysis of adversarial and differentially private learning.
result Stronger regret and privacy error guarantees with smoothed adversaries.
Paper addresses hybrid learning with constrained adversaries, achieving optimal performance.
problem Hybrid learning problem with i.i.d. features and adversarial labels.
method Structured adversarial setting, efficient algorithm with ERM oracle.
result Oracle-efficient algorithm with regret scaling with Rademacher complexity.
In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which permits online robustness training alongside Q networks, while preserving competitive performance. We show that RS-DQN can be combined with…
Unified meta-algorithm improves average performance across similar tasks in adversarial bandits.
problem Improving performance across multiple similar tasks in adversarial bandit settings.
method Unified meta-algorithm for multi-armed bandits and bandit linear optimization, tuning initialization, step-size, and entropy parameters.
result Unified meta-algorithm yields setting-specific guarantees for MAB and BLO, improving task-averaged regret.
Study improves privacy-preserving online prediction from experts with speed-ups.
problem Privacy-preserving online prediction from experts with speed-ups.
method Differentially private federated online prediction algorithms.
result Achieves m m m -fold regret speed-up with low-loss expert in federated setting. Paper optimizes GAIL for online and offline learning with linear approximations.
problem Imitation learning from expert demonstrations with linear function approximations.
method Proposes optimistic and pessimistic algorithms for online and offline settings.
result Proves optimality and efficiency of proposed algorithms.
We consider online learning in an adversarial, non-convex setting under the assumption that the learner has an access to an offline optimization oracle. In the general setting of prediction with expert advice, Hazan et al. (2016) established that in the optimization-oracle model, online learning requires exponentially …
This paper proposes an online knowledge distillation method that transfers feature map information in addition to class probabilities.
problem Previous online knowledge distillation methods only utilized class probabilities, missing feature map information.
method Adversarial training framework to transfer feature map information; multiple networks trained simultaneously with discriminators.
result Our method performs better than direct alignment methods and is more suitable for online distillation.
New algorithm learns halfspaces with adversarial noise efficiently.
problem Learning halfspaces in the presence of adversarial noise.
method Polynomial-time Perceptron-like online active learning algorithm.
result Near-optimal label and sample complexity with isotropic log-concave marginal distribution.
As online systems based on machine learning are offered to public or paid subscribers via application programming interfaces (APIs), they become vulnerable to frequent exploits and attacks. This paper studies adversarial machine learning in the practical case when there are rate limitations on API calls. The adversary …
Motivated by online advertising auctions, we consider repeated Vickrey auctions where goods of unknown value are sold sequentially and bidders only learn (potentially noisy) information about a good's value once it is purchased. We adopt an online learning approach with bandit feedback to model this problem and derive …
Improved online learning for hidden-convex losses achieves optimal regret.
problem Adversarial online learning with nonconvex losses that become convex after reparameterization.
method Algorithmic equivalence between OGD and OMD on convex losses, with Hessian compatibility condition.
result OGD achieves O ( T ) \mathcal{O}(\sqrt{T}) O ( T ) regret for hidden-convex losses, matching optimal rate. New algorithms achieve small prediction regret for learning from overlapping groups.
problem Online multi-group learning with fairness applications.
method Oracle-efficient algorithms for groups not explicitly enumerated.
result Sublinear regret in various settings.
Study online learning with off-policy feedback in adversarial bandit problems.
problem Learning with limited direct feedback in sequential decision making.
method Proposed algorithms that adapt pessimistic reward estimators to handle unknown behavior policy.
result Guaranteed regret bounds scaling with policy mismatch, improving performance against well-covered comparators.
New algorithm tackles adversarial bandits with arbitrary strategies.
problem Adversarial bandit problem against arbitrary strategies.
method Adopted master-base framework using online mirror descent method (OMD). Proposed adaptive learning rates for OMD.
result Achieved improved regret bounds compared to previous methods.
Adversarial online multi-task RL with task separation.
problem Minimize regret in an adversarial online multi-task setting with unknown MDPs.
method Prove minimax and instance-specific lower bounds, develop a clustering algorithm with optimal sample complexity and regret.
result Tight sample complexity and regret bounds for adversarial online multi-task RL.
New insights into learning from distributional adversaries and private data.
problem Understanding minimal assumptions for learning and generalization under distributional constraints.
method Generalized smoothness as a characterization of learnability and privacy under distributional adversaries.
result Near complete characterization of families that admit learnability and privacy under distributional adversaries.
Algorithm adapts to shifting domains with minimal label queries.
problem Adaptive learning in online machine learning systems with domain shifts.
method Adaptive algorithm balancing regret and label queries for hidden domains.
result Achieves lower regret compared to uniform and greedy queries.
New bounds show complexity of adversarial decision making.
problem Understanding sample efficiency in adversarial decision making.
method New upper and lower bounds on Decision-Estimation Coefficient.
result Decision-Estimation Coefficient is necessary and sufficient for low regret in adversarial decision making.