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.

168,742 papers · 148 categories

Trend · papers per month

285684112 · May 202619922001200920172026
48 results for reward drift

Incentivized exploration improves MAB performance under reward drift.

problem Improving exploration in multi-armed bandits with biased feedback.
method Analysis of three MAB algorithms (UCB, ε-Greedy, Thompson Sampling) under drifted reward feedback.
result All algorithms achieve O(logT)\mathcal{O}(\log T) regret and compensation under drifted reward.

The paper enhances preference learning by incorporating response time data.

problem Lack of temporal information in user decision-making for reward model learning.
method Integrates response time alongside binary choice data using the EZ model and Neyman-orthogonal loss functions.
result Response time-augmented approach reduces error rates from exponential to polynomial scaling, improving sample efficiency.

Study optimal reward schemes for inducing desired player performance in risky contests.

problem Designing optimal rewards to encourage desired performance levels in risky contests.
method Analyzed the optimal reward schemes for inducing average and specific rank performance.
result Optimal reward schemes can have surprising shapes, not just related to inequality.

New algorithm for non-stationary bandits with slow drifts.

problem Minimizing dynamic regret in non-stationary bandits with slowly varying rewards.
method Extends Successive Elimination to non-stationary bandits with a novel gap profile characterization.
result First instance-dependent regret upper bound for slowly varying non-stationary bandits.

A new method helps deep learning systems adapt to changing conditions.

problem Deep learning systems struggle with environmental drifts and long healing cycles.
method Intentional forgetting integrated into continual learning to overcome issues.
result Dr. DRL reduces healing time and fine-tuning episodes by 18.74% and 17.72% respectively.

In this paper long-run risk sensitive optimisation problem is studied with dyadic impulse control applied to continuous-time Feller-Markov process. In contrast to the existing literature, focus is put on unbounded and non-uniformly ergodic case by adapting the weight norm approach. In particular, it is shown how to com…

2019-06-14abs ↗pdf ↗

Unified approach for non-stationary linear bandits with dynamic regret.

problem Non-stationary linear bandits with round-specific feasible actions and drifting reward models.
method Unified misspecification-reduction viewpoint, restarting algorithms with misspecification-dependent regret guarantees.
result Optimal \(T^{2/3}P_T^{1/3}\) dynamic-regret dependence for both linear bandits and contextual linear bandits.

An algorithm for efficient experimentation in a dynamic environment with personalized preferences and context drifts.

problem Efficiently recommending decisions to users with personalized preferences in a context where the environment is changing over time.
method Dri-MED, inspired from the linear version of the MED strategy, adapted to handle non-stationary heteroskedastic noise.
result The instance-dependent regret scales as $ ilde{\mathcal O}\left(\fracκ{ ildeΔ}d^2(\log(T) ight)$, with ildeΔ ildeΔ being the constraint-aware sub-optimality gap.

Paper tackles non-monotonic resource utilization in sequential decision-making.

problem Sequential decision-making under uncertainty with resource constraints.
method Introduces a new MDP policy with constant regret against LP relaxation.
result Develops a learning algorithm with logarithmic regret for unknown outcome distributions.

A new algorithm tackles delayed combinatorial semi-bandit with causal relations.

problem Optimizing decisions in a non-stationary environment with delayed and causally related rewards.
method Formalized as a non-stationary delayed combinatorial semi-bandit problem, the approach models causal relations with a directed graph in a stationary structural equation model. The agent learns these relations from delayed feedback to optimize decisions.
result Proved a regret bound for the proposed algorithm's performance.

This paper tackles robust policy learning under concept drifts, improving upon existing methods.

problem Tackles robust policy learning under concept drifts, improving upon existing methods.
method Develops a doubly-robust estimator and a learning algorithm to maximize policy value within a given policy class.
result The proposed algorithm achieves sub-optimality gap of the order κ(Π)n1/2κ(Π)n^{-1/2}, demonstrating substantial improvement over existing benchmarks.

Algorithm learns diffusion processes with high-dimensional state spaces.

problem Stochastic control of unbounded diffusion processes with high-dimensional state spaces.
method Adaptive partitioning and learning algorithm that refines discretization based on estimation bias and statistical confidence.
result Established regret bounds that depend on problem parameters, extending to unbounded diffusion processes.

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.

DRO-REBEL improves LLM alignment by robustly updating models online.

problem Overfitting and drifting of LLMs during RLHF.
method DRO-REBEL uses type-pp Wasserstein, KL, and χ2χ^2 ambiguity sets for robust online updates.
result DRO-REBEL achieves faster convergence and better performance than prior methods.

This review covers learning under concept drift, including detection, understanding, and adaptation.

problem Unforeseeable changes in data distribution over time impact machine learning performance.
method Reviews and analyzes methodologies and techniques for concept drift detection, understanding, and adaptation.
result Establishes a framework for learning under concept drift with three main components.

In this paper we consider stochastic optimization problems for an ambiguity averse decision maker who is uncertain about the parameters of the underlying process. In a first part we consider problems of optimal stopping under drift ambiguity for one-dimensional diffusion processes. Analogously to the case of ordinary o…

2011-10-18abs ↗pdf ↗

Bayesian bandits misspecification affects UX optimization, revealing new models.

problem Misspecification of value models in Bayesian bandits impacts UX optimization.
method Formulated UXO as a restless, sleeping bandit with unobserved confounders and optional stopping. Provided model extensions to address misspecifications.
result Common misspecifications lead to sub-optimal rewards, demonstrating overdispersion's effects on bandit performance.

This research identifies flaws in drift detection methods and creates adversarial data streams to exploit them.

problem The challenge of detecting data distribution changes (drift) in real-time systems.
method Developed adversarial data streams to show weaknesses in existing drift detection schemes.
result Demonstrated that common drift detection methods can be fooled by adversarial data streams.

New RL method tackles dynamic MDPs with evolving rewards and states.

problem Dynamic MDPs with evolving rewards and states.
method Sliding Window Upper-Confidence bound for Reinforcement Learning (SWUCRL2-CW) and Bandit-over-Reinforcement Learning (BORL).
result Achieves dynamic regret bound for non-stationary MDPs.

Classifiers operating in a dynamic, real world environment, are vulnerable to adversarial activity, which causes the data distribution to change over time. These changes are traditionally referred to as concept drift, and several approaches have been developed in literature to deal with the problem of drift handling an…

2018-03-24abs ↗pdf ↗

Classifies polynomial growth solutions to drift-harmonic equations on asymptotically paraboloidal manifolds.

problem Classifying polynomial growth solutions to drift-harmonic equations on specific types of manifolds.
method Inductive argument that alternates between constructing and asymptotically controlling drift-harmonic functions.
result All drift-harmonic functions with polynomial growth asymptotically separate variables and dimensions of spaces are computed.

Detects drifts in data for classification tasks using constrained embeddings.

problem Drifts in data affect model performance; unsupervised methods ignore label information.
method Task-sensitive semi-supervised drift detection with constrained low-dimensional embedding.
result Successfully detects real drifts affecting classification performance.

Concept drift is formally defined as the change in joint distribution of a set of input variables X and a target variable y. The two types of drift that are extensively studied are real drift and virtual drift where the former is the change in posterior probabilities p(y|X) while the latter is the change in distributio…

2019-09-25abs ↗pdf ↗

PDD detects concept drift using explainable AI, improving model performance in dynamic environments.

problem Detecting and adapting to concept drift in predictive models.
method Profile Drift Detection (PDD) using Partial Dependence Profiles (PDPs).
result PDD outperforms existing methods in detecting concept drift and maintaining high predictive performance.

Paper proposes a framework to detect adversarial concept drifts under poisoning attacks.

problem Adversarial concept drift in data streams.
method Augmented Restricted Boltzmann Machine with improved gradient computation and energy function.
result High robustness and efficacy of the proposed drift detection framework in adversarial scenarios.

CURIE uses cellular automata to detect concept drift in data streams.

problem Detecting changes in data distribution (concept drift) in data streams.
method CURIE represents data stream distribution in a cellular automata grid and uses its neighborhood rule to detect changes.
result CURIE, when hybridized with base learners, performs competitively in detection metrics and classification accuracy.

Gradient-based methods for games suffer from discrete update steps that cause drift, affecting performance.

problem Gradient-based methods for two-player games suffer from drift due to discrete update steps.
method Derived modified continuous dynamical systems to closely follow the discrete dynamics of games.
result Identified distinct components of discretization drift that can alter or destabilize game performance.