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. 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…
New algorithm reduces control error in systems with changing dynamics.
problem Online control of systems with time-varying linear dynamics.
method Introduces adaptive regret metric and a novel meta-algorithm.
result First adaptive regret bound for online convex optimization with memory.
Study risk-sensitive reinforcement learning with Lipschitz dynamic risk measures, establishing regret bounds.
problem Risk-sensitive reinforcement learning in Markov decision processes.
method Two model-based algorithms for Lipschitz dynamic risk measures, focusing on regret bounds.
result Upper bounds demonstrate optimal dependencies on actions and episodes, reflecting risk sensitivity vs. sample complexity trade-off.
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…
Study optimal control in unknown nonlinear systems with near-optimal regret bound.
problem Sequential control in unknown, nonlinear dynamical systems.
method LC^3 algorithm, based on information theory.
result Near-optimal O ( T ) O(\sqrt{T}) O ( T ) regret bound for episodic settings. 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. As a metric to measure the performance of an online method, dynamic regret with switching cost has drawn much attention for online decision making problems. Although the sublinear regret has been provided in many previous researches, we still have little knowledge about the relation between the dynamic regret and the s…
This work focuses on dynamic regret of online convex optimization that compares the performance of online learning to a clairvoyant who knows the sequence of loss functions in advance and hence selects the minimizer of the loss function at each step. By assuming that the clairvoyant moves slowly (i.e., the minimizers c…
Dynamic pricing algorithms can work with covariates without i.i.d. assumptions.
problem Dynamic pricing with covariates under a generalized linear demand model.
method UCB and Thompson sampling-based pricing algorithms.
result Achieves an O ( d T log T ) O(d\sqrt{T}\log T) O ( d T log T ) regret upper bound without i.i.d. covariates assumption. 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 i l d e O ( T V T ∨ log T ) ilde O(\sqrt{TV_T} \vee \log T) i l d e O ( T V T ∨ log T ) and i l d e O ( d T V T ∨ d log T ) ilde O(\sqrt{dTV_T} \vee d\log T) i l d e O ( d T V T ∨ d log T ) dynamic regret for strongly convex and exp-concave losses, respectively. Study on learning to predict dynamical systems without assuming their structure.
problem Learning to predict the next state of a dynamical system with unknown evolution function.
method Defined new combinatorial measures to quantify mistake and regret bounds in realizable and agnostic settings.
result In the realizable setting, the number of mistakes can grow arbitrarily with time.
New algorithm reduces dynamic regret in time-varying movement costs.
problem Dynamic regret in online convex optimization with time-varying movement costs.
method Introduced a novel algorithm for time-varying movement costs, achieving comparator-adaptive dynamic regret bound.
result Established first comparator-adaptive dynamic regret bound of O ~ ( ( M 2 + M P T ) ( T + ∑ t λ t ) ) \widetilde{\mathcal{O}}(\sqrt{(M^2+MP_T)(T+\sum_t λ_t)}) O ( ( M 2 + M P T ) ( T + ∑ t λ t ) ) . New algorithm reduces learning regret in multi-agent systems with unknown dynamics.
problem Challenges in decentralized learning due to unknown dynamics and lack of communication.
method Proposed MARL algorithm for two-agent LQ systems with unknown dynamics and one-directional communication.
result Achieved O ( T ) O(\sqrt{T}) O ( T ) regret bound for multi-agent LQ systems with certain communication patterns. New algorithms for online learning without boundedness or Lipschitz loss assumptions.
problem Online learning with unbounded domains and non-Lipschitz losses.
method Developed an algorithm with a specific regret bound and used it for saddle-point optimization.
result First algorithm achieving non-trivial dynamic regret in an unbounded domain for non-Lipschitz losses.
New algorithm learns LQR with O ( T ) O(\sqrt{T}) O ( T ) regret using Langevin dynamics and excitation.
problem Learning LQR with a O ( T ) O(\sqrt{T}) O ( T ) regret bound. method Thompson sampling with Langevin dynamics and excitation mechanism.
result Achieved O ( T ) O(\sqrt{T}) O ( T ) regret bound for LQR learning. 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. We study optimal regret bounds for control in linear dynamical systems under adversarially changing strongly convex cost functions, given the knowledge of transition dynamics. This includes several well studied and fundamental frameworks such as the Kalman filter and the linear quadratic regulator. State of the art met…
Study online control of unknown time-varying systems with negative and positive results.
problem Online control of time-varying systems with unknown dynamics.
method Algorithmic upper bounds and lower bounds for different policy classes.
result Sublinear adaptive regret bounds for Disturbance Response policies.
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.
This paper describes a new online convex optimization method which incorporates a family of candidate dynamical models and establishes novel tracking regret bounds that scale with the comparator's deviation from the best dynamical model in this family. Previous online optimization methods are designed to have a total a…
New algorithm adapts to unknown demand smoothness for dynamic pricing.
problem Dynamic pricing with unknown Hölder smoothness of demand function.
method Self-similarity condition and adaptive algorithm.
result Adaptive algorithm achieves minimax optimal regret without prior knowledge of smoothness.
Algorithm reduces regret in partially observable systems by learning dynamics and using optimistic control.
problem Minimizing regret in partially observable linear quadratic control systems with unknown dynamics.
method ExpCommit algorithm that learns model parameters and uses optimism in uncertainty.
result End-to-end sublinear regret upper bound of O ~ ( T 2 / 3 ) \tilde{\mathcal{O}}(T^{2/3}) O ~ ( T 2/3 ) for ExpCommit. New algorithms reduce dynamic regret for convex and smooth functions in non-stationary environments.
problem Online convex optimization in non-stationary environments.
method Proposed novel online algorithms exploiting smoothness to reduce dynamic regret.
result Dynamic regret improved to O ( T ) \mathcal{O}(T) O ( T ) for convex and smooth functions. Algorithm tackles adaptive discretization in adversarial Lipschitz bandits for dynamic pricing and auctions.
problem Adaptive discretization in adversarial Lipschitz bandits.
method Adversarial Zooming algorithm for adaptive discretization.
result First algorithm for adversarial Lipschitz bandits with instance-dependent regret bounds.
The paper improves competitive and dynamic regret bounds for smoothed online learning.
problem Smoothed online learning with hitting and switching costs.
method Optimization problems to minimize hitting cost, dynamic regret modification of existing algorithms.
result Improved competitive and dynamic regret bounds for various function classes.
Study minimax rates for online learning with time-varying dynamics.
problem Online learning with time-varying state and cost dynamics.
method Non-constructive upper and lower bounds, complexity and stability terms.
result Characterization of minimax rates and necessary conditions for learnability.
New algorithm tackles non-stationary combinatorial semi-bandit problems with optimal regret bounds.
problem Non-stationary combinatorial semi-bandit problems in switching and dynamic environments.
method Developed algorithms for both switching and dynamic cases, achieving nearly optimal regret bounds.
result Achieved nearly optimal regret bounds in both switching and dynamic cases.
New method reduces dynamic regret for non-stationary bandits.
problem Non-stationary stochastic multi-armed bandit problem with changing optimal arm.
method Proposes a method achieving near-optimal dynamic regret without prior knowledge of changes.
result Achieves O ~ ( K N ( S + 1 ) ) \widetilde O(\sqrt{K N(S+1)}) O ( K N ( S + 1 ) ) dynamic regret. In this short note we consider a dynamic assortment planning problem under the capacitated multinomial logit (MNL) bandit model. We prove a tight lower bound on the accumulated regret that matches existing regret upper bounds for all parameters (time horizon T T T , number of items N N N and maximum assortment capacity K K K )…
New algorithms reduce dynamic regret in online MDPs with changing losses.
problem Online MDPs with adversarial loss changes and known transitions.
method Dynamic regret measure, novel ensemble algorithms for three models.
result Provably optimal dynamic regret bounds for episodic SSP, improved bounds for predictable environments.
New RL algorithm tackles nonstationary MDPs with linear approximations and varying rewards.
problem Nonstationary reinforcement learning with evolving reward and state transition functions.
method Developed a new algorithm LSVI-UCB-Restart with periodic restart, and parameter-free Ada-LSVI-UCB-Restart for unknown variation budgets.
result First minimax dynamic regret lower bound for nonstationary linear MDPs and linear MDPs lower bound.
In this paper, we study online convex optimization in dynamic environments, and aim to bound the dynamic regret with respect to any sequence of comparators. Existing work have shown that online gradient descent enjoys an O ( T ( 1 + P T ) ) O(\sqrt{T}(1+P_T)) O ( T ( 1 + P T )) dynamic regret, where T T T is the number of iterations and P T P_T P T is the path-le…
Reduces dynamic regret to static problem in RKHS.
problem Minimizing cumulative loss in online convex optimization.
method Reduces dynamic regret to static regret problem in RKHS.
result Optimal dynamic regret guarantees for linear losses and new bounds for exp-concave and improper linear regression.
Improved regret bounds for online convex optimization under stochastic and adversarial settings.
problem Interpolating between stochastic and adversarial online convex optimization.
method Optimistic online mirror descent (OMD) for the Stochastically Extended Adversarial (SEA) model.
result Established new regret bounds for various function classes.
This study develops a dynamic inverse optimization framework to recover hidden, time-varying preferences from observed allocation trajectories.
problem The gap between classical optimization theory and real-world practice, especially in the presence of drift and shocks.
method Dynamic inverse optimization framework using a drift-aware estimator grounded in convex analysis and online learning theory.
result Sharp static and dynamic regret bounds for the framework, demonstrating its responsiveness to gradual drift and sudden shocks.
New RL approach learns dynamic VCG mechanisms in unknown MDP environments.
problem Learning dynamic VCG mechanisms in unknown MDP environments.
method Reward-free online RL for exploration, combined with function approximation.
result Regret bound of O ~ ( T 2 / 3 ) \tilde{\mathcal{O}}(T^{2/3}) O ~ ( T 2/3 ) for dynamic VCG mechanism learning. Sequential screening and dynamic regret in multi-armed bandits with arriving arms
problem Sequential experimentation with expanding arm set
method UCB-AA with preliminary screening
result Regret bounds depend on arrival process
New algorithm reduces dynamic regret by adapting to comparator complexity.
problem Nonstationary sequential decision making with unbounded domains.
method Sparse coding framework to adapt to comparator complexity.
result Improves dynamic regret bounds by adapting to comparator energy and sparsity.
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.
Decentralized optimization on dynamic manifolds with improved regret bound.
problem Optimizing on nonstationary Riemannian manifolds in decentralized systems.
method Decentralized projected Riemannian gradient descent with weighted Frechet mean consensus.
result Achieved dynamic regret bound of O ( T ( 1 + P T ) / ( 1 − σ 2 ( W ) ) ) {\cal O}(\sqrt{T(1+P_T)}/\sqrt{(1-σ_2(W))}) O ( T ( 1 + P T ) / ( 1 − σ 2 ( W )) ) . Transformers achieve near-optimal dynamic regret in non-stationary reinforcement learning.
problem Understanding and handling non-stationary environments in reinforcement learning.
method Demonstrated that transformers can achieve nearly optimal dynamic regret bounds in non-stationary settings.
result Transformers can approximate and learn strategies for non-stationary environments, matching or outperforming existing expert algorithms.
In this paper, we consider the problem of prediction with expert advice in dynamic environments. We choose tracking regret as the performance metric and develop two adaptive and efficient algorithms with data-dependent tracking regret bounds. The first algorithm achieves a second-order tracking regret bound, which impr…
Study learns optimal bidding strategy in auctions with dynamic values and aggregated feedback.
problem Optimizing bidding in auctions with time-dependent values and limited feedback.
method Combines plug-in estimators with differential-equation characterization of optimal policy.
result Achieves near optimal regret bounds for learning optimal policy.
Proposes a method to learn policies from offline data with reduced bias.
problem Learning policies from offline data with reduced bias and complexity constraints.
method Cross-fitted debiasing device for policy learning from offline data.
result Achieves N \sqrt N N regret for complex policy classes with a product-of-errors nuisance remainder. Paper presents a privacy-preserving method for dynamic assortment selection.
problem Personalized assortment recommendations with data privacy concerns.
method Perturbed upper confidence bound method integrating calibrated noise.
result Policy satisfies Joint Differential Privacy (JDP) with near-optimal regret bound.
Optimal control in changing systems without strong convexity assumptions.
problem Adversarial changes in convex costs for unknown linear systems.
method Non-convex lower confidence bounds and computationally-efficient regret minimization.
result Achieves T \smash{\sqrt{T}} T -regret rate, optimal compared to best stabilizing controller. Two algorithms achieve optimal logarithmic regret in feature-based dynamic pricing.
problem Optimal pricing for products with features based on online learning.
method Developed EMLP and ONSP algorithms for stochastic and adversarial settings, proving O ( d log T ) O(d\log{T}) O ( d log T ) regret bounds. result Achieved optimal O ( d log T ) O(d\log{T}) O ( d log T ) regret, improving over existing bounds.