Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,932 papers · 148 categories

Trend · papers per month

8.3%16.7%25.0%33.3% · Jun 202019922001200920172026
48 results for optimal aggregate regret

Optimized Q-learning reduces regret in state-aggregated MDPs.

problem Reducing regret in reinforcement learning with state aggregation.
method Optimistic Q-learning applied to fixed-horizon episodic MDPs with aggregated states.
result Regret bound of ildeO(H5MK+εHK) ilde{\mathcal{O}}(\sqrt{H^5 M K} + εHK), independent of states and actions.

Study online learning in MDPs with aggregate bandit feedback, achieving low regret in both stochastic and adversarial settings.

problem Online learning in finite-horizon episodic MDPs with aggregate bandit feedback.
method Best-of-both-worlds (BOBW) algorithms using FTRL over occupancy measures, self-bounding techniques, and new loss estimators.
result First BOBW algorithms for episodic tabular MDPs with aggregate bandit feedback achieving O(logT)O(\log T) regret in stochastic and O(T){O}(\sqrt{T}) regret in adversarial settings.

The article is devoted to investigating the application of aggregating algorithms to the problem of the long-term forecasting. We examine the classic aggregating algorithms based on the exponential reweighing. For the general Vovk's aggregating algorithm we provide its generalization for the long-term forecasting. For …

2018-03-18abs ↗pdf ↗

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.

Policy gradient methods with aggregated states can achieve better performance than approximate policy iteration.

problem Approximation errors in policy and value function approximations.
method State-aggregated representations and policy gradient methods.
result Policy gradient methods can achieve a per-period regret bounded by ε, while approximate policy iteration and value iteration have a higher regret.

Study optimal policy regret in partially observable Markov games with adaptive opponents.

problem Optimal sequential decision-making in partially observable environments against strategic, adaptive opponents.
method An epoch-based optimistic maximum-likelihood algorithm that selects one policy per epoch using confidence sets built cumulatively from past data.
result Achieves ildeO(T) ilde{O}(\sqrt{T}) policy regret for fixed problem parameters, with explicit dependence on horizon, adversary memory, confidence radius, and aggregate Eluder dimension.

Paper addresses robust federated linear bandits against Byzantine attacks.

problem Byzantine attacks on a small fraction of agents in federated learning.
method Proposes a geometric median-based robust aggregation oracle.
result Achieves sublinear regret bound of ildeO(T3/4) ilde{\mathcal{O}}({T^{3/4}}) robust to fewer than half Byzantine agents.

The paper explores trade-offs between regret and variance in online learning algorithms.

problem Investigating the trade-offs between regret and variance in online learning.
method Analysis of the Exponentially Weighted Average (EWA) algorithm and its variants.
result A variant of EWA either achieves negative regret or guarantees a logarithmic bound on both variance and regret.

We prove a lower bound for feature dimension in linear MDPs and propose a novel dynamics aggregation framework.

problem The limitation of feature dimension in linear MDPs and the need for efficient hierarchical reinforcement learning.
method We propose a novel dynamics aggregation framework based on structural dynamics and design a provably efficient hierarchical reinforcement learning algorithm.
result Our algorithm achieves a regret of ildeO(dψ3/2H3/2NT) ilde{O} ( d_ψ^{3/2} H^{3/2}\sqrt{ N T} ) and meets the condition dψ3Nd3d_ψ^3 N \ll d^{3} in most real-world environments.

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(TlogT)O(\sqrt{T} \log T) expected regret compared to best weights.

We introduce a new recursive aggregation procedure called Bernstein Online Aggregation (BOA). The exponential weights include an accuracy term and a second order term that is a proxy of the quadratic variation as in Hazan and Kale (2010). This second term stabilizes the procedure that is optimal in different senses. We…

2014-04-04abs ↗pdf ↗

Nonparametric Thompson Sampling achieves optimal regret for risk-averse bandits with sub-Gaussian rewards.

problem Optimizing risk-averse bandit problems with sub-Gaussian rewards.
method Anchor-free nonparametric Thompson Sampling algorithm ρextNPTSSGρ ext{-}NPTS_{\mathrm{SG}}.
result Achieves regret matching the instance-dependent lower bound to leading order in logn\log n.

Mixability of a loss is known to characterise when constant regret bounds are achievable in games of prediction with expert advice through the use of Vovk's aggregating algorithm. We provide a new interpretation of mixability via convex analysis that highlights the role of the Kullback-Leibler divergence in its definit…

2014-03-10abs ↗pdf ↗

New approach optimizes policies in adversarial MDPs using adversarial learning.

problem Optimizing policies in adversarial Markov decision processes.
method Adversarial learning on advantage functions, extending previous reductions.
result Stronger regret criteria and performance guarantees for policy optimization.

We use online convex optimization (OCO) for setpoint tracking with uncertain, flexible loads. We consider full feedback from the loads, bandit feedback, and two intermediate types of feedback: partial bandit where a subset of the loads are individually observed and the rest are observed in aggregate, and Bernoulli feed…

2017-09-12abs ↗pdf ↗

Improved regret bound for online learning in unknown MDPs.

problem Online learning in unknown episodic MDPs with changing loss functions.
method Adapts adversarial MDP model to convex performance criteria using entropic regularization.
result Achieved ildeO(LXAT) ilde{O}(L|X|\sqrt{|A|T}) regret bound.

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}) regret for the online Markov Decision Process with KK episodes.

Optimal scheme minimizes deviation in federated transfer learning for kernel regression.

problem Minimizing cumulative deviation in federated transfer learning across multiple datasets.
method Regret-optimal iterative scheme for continual communication between nodes and server.
result Explicit updates for the regret-optimal algorithm in finite-rank kernel regression.

We study a variant of the stochastic KK-armed bandit problem, which we call "bandits with delayed, aggregated anonymous feedback". In this problem, when the player pulls an arm, a reward is generated, however it is not immediately observed. Instead, at the end of each round the player observes only the sum of a number…

2017-09-20abs ↗pdf ↗

New algorithm reduces regret bounds for Bayesian optimization with unknown hyperparameters.

problem Optimizing black-box functions with unknown hyperparameters, especially length scale.
method Length Scale Balancing (LB) - aggregating multiple surrogate models with varying length scales.
result LB achieves a regret bound only logaritically away from the oracle algorithm.

Improved multiclass logistic regression with lower computational complexity.

problem High computational complexity in existing methods for multiclass logistic regression.
method Developed a new algorithm that achieves a lower computational complexity.
result Achieved a regret of O(log(Bn))O(\log(Bn)) with computational complexity O(n1.5)O(n^{1.5}).

Algorithm reduces regret in distributed kernel bandits with shared randomness.

problem Minimizing regret in collaborative function maximization.
method Uniform exploration at local agents and shared randomness with central server.
result Achieves optimal regret order with sublinear communication cost.

Paper develops a discounted algorithm for online convex optimization that adapts to unknown discount factors.

problem Developing an algorithm that can adapt to an unknown discount factor in online convex optimization.
method Smoothed Online Gradient Descent (SOGD) with Discounted-Normal-Predictor (DNP).
result Achieves a uniform O(logT/1λ)O(\sqrt{\log T/1-λ}) discounted regret across a continuous interval of discount factors.

New algorithm reduces regret in CBs with time-varying models.

problem Designing robust interventions in CBs with unknown, fluctuating causal models.
method Proposes a robust CB algorithm with upper and lower bounds on regret.
result Achieves nearly optimal ildeO(T) ilde{\mathcal{O}}(\sqrt{T}) regret under certain conditions.

The paper tackles personalized policy learning from diverse data sources in a federated setting.

problem Learning personalized decision policies from observational bandit feedback across multiple heterogeneous data sources.
method Introduces a novel regret analysis for distinguishing global and local regret, and presents a federated policy learning algorithm using local policies trained with doubly robust offline policy evaluation strategies.
result Establishes finite-sample upper bounds on global and local regret, characterizing them by source heterogeneity and distribution shift.

Two approaches integrate qualitative views into portfolio optimization, showing aggregation methods outperform robust optimization.

problem Incorporating qualitative views into portfolio optimization models.
method Robust optimization and order aggregation methods.
result Aggregation methods outperform robust optimization in portfolio performance analysis.

The paper develops a method for forecasting power consumption at various levels of aggregation.

problem Forecasting power consumption at different levels of household aggregation.
method Three-step process: feature generation, aggregation, and projection.
result The method provides theoretical guarantees on prediction error and performs well on real data.

Algorithm aggregates rewards from multiple players to learn related tasks in online bandit learning.

problem Learning related but slightly different tasks in an online setting with heterogeneous feedback.
method RobustAgg(ε)(ε) algorithm that aggregates rewards from different players.
result Achieves instance-dependent regret guarantees and nearly matching lower bounds.

We consider a variation on the problem of prediction with expert advice, where new forecasters that were unknown until then may appear at each round. As often in prediction with expert advice, designing an algorithm that achieves near-optimal regret guarantees is straightforward, using aggregation of experts. However, …

2017-08-31abs ↗pdf ↗

Study online monotone density estimation with expert aggregation and log-optimal calibration.

problem Online monotone density estimation and log-optimal calibration.
method Proposed two online estimators: Grenander estimator and expert aggregation estimator.
result Online estimators achieve O(n1/3)O(n^{1/3}) cumulative log-likelihood gap and nlogn\sqrt{n\log{n}} pathwise regret bound.

Paper proposes OPF policy for fair resource allocation with sublinear regret.

problem Fair resource allocation in an online setting against an unrestricted adversary.
method Online Proportional Fair (OPF) policy achieving approximate sublinear regret.
result OPF policy achieves cαc_α-approximate sublinear regret with cα1.445c_α \leq 1.445.

Improved Thompson Sampling reduces regret in contextual bandits and reinforcement learning.

problem Thompson Sampling's exploration is insufficient in some contexts.
method Developed Feel-Good Thompson Sampling to address exploration issues.
result Feel-Good Thompson Sampling reduces regret compared to standard Thompson Sampling.

Study non-oblivious adversarial bandits with delayed feedback and propose algorithms with improved regret bounds.

problem Adversarial bandit problem with delayed, composite anonymous feedback.
method Propose wrapper algorithm for non-oblivious delay setting, achieving o(T)o(T) policy regret.
result Achieve o(T)o(T) policy regret for many adversarial bandit problems with bounded memory loss sequences.

Regret minimization is a powerful tool for solving large-scale problems; it was recently used in breakthrough results for large-scale extensive-form game solving. This was achieved by composing simplex regret minimizers into an overall regret-minimization framework for extensive-form game strategy spaces. In this paper…

2018-11-06abs ↗pdf ↗

New algorithm tackles multi-agent bandits with heavy-tailed data.

problem Maximizing system performance in multi-agent settings with heavy-tailed data.
method Algorithm exploits hub-like structures and synchronization among clients.
result Regret bound of O(M11αlogT)O(M^{1 -\frac{1}α} \log{T}) for homogeneous settings, O(MlogT)O(M \log{T}) for heterogeneous.