Search Results for author:
Found 22 papers, 2 papers with code
Provably Robust DPO: Aligning Language Models with Noisy Feedback
Our experiments on IMDb sentiment generation and Anthropic's helpful-harmless dataset show that rDPO is robust to noise in preference labels compared to vanilla DPO and other heuristics proposed by practitioners.
Provably Sample Efficient RLHF via Active Preference Optimization
Experimental evaluations on a human preference dataset validate \texttt{APO}'s efficacy as a sample-efficient and practical solution to data collection for RLHF, facilitating alignment of LLMs with human preferences in a cost-effective and scalable manner.
GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval
Given a query and a document corpus, the information retrieval (IR) task is to output a ranked list of relevant documents.
Differentially Private Reward Estimation with Preference Feedback
Within a standard minimax estimation framework, we provide tight upper and lower bounds on the error in estimating $\theta^*$ under both local and central models of DP.
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards
Under each framework, we consider both joint differential privacy (JDP) and local differential privacy (LDP) models.
On Differentially Private Federated Linear Contextual Bandits
We first establish privacy and regret guarantees under silo-level local differential privacy, which fix the issues present in state-of-the-art algorithm.
Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference
Furthermore, while the previous result is shown to hold only in the asymptotic regime (as $n \to \infty$), our result for these "locally rich" action spaces is any-time.
Model Selection in Reinforcement Learning with General Function Approximations
We consider model selection for classic Reinforcement Learning (RL) environments -- Multi Armed Bandits (MABs) and Markov Decision Processes (MDPs) -- under general function approximations.
Distributed Differential Privacy in Multi-Armed Bandits
This protocol achieves ($\epsilon,\delta$) or approximate-DP guarantee by sacrificing an additional additive $O\!\left(\!\frac{K\log T\sqrt{\log(1/\delta)}}{\epsilon}\!\right)\!$ cost in $T$-step cumulative regret.
Shuffle Private Linear Contextual Bandits
Prior work largely focus on two trust models of DP: the central model, where a central server is responsible for protecting users sensitive data, and the (stronger) local model, where information needs to be protected directly on user side.
Bregman Deviations of Generic Exponential Families
For the practitioner, we instantiate this novel bound to several classical families, e. g., Gaussian, Bernoulli, Exponential, Weibull, Pareto, Poisson and Chi-square yielding explicit forms of the confidence sets and the Bregman information gain.
Differentially Private Regret Minimization in Episodic Markov Decision Processes
We study regret minimization in finite horizon tabular Markov decision processes (MDPs) under the constraints of differential privacy (DP).
Adaptive Control of Differentially Private Linear Quadratic Systems
In this paper, we study the problem of regret minimization in reinforcement learning (RL) under differential privacy constraints.
Model Selection for Generic Reinforcement Learning
We propose and analyze a novel algorithm, namely \emph{Adaptive Reinforcement Learning (General)} (\texttt{ARL-GEN}) that adapts to the smallest such family where the true transition kernel $P^*$ lies.
Value Function Approximations via Kernel Embeddings for No-Regret Reinforcement Learning
We consider the regret minimization problem in reinforcement learning (RL) in the episodic setting.
No-regret Algorithms for Multi-task Bayesian Optimization
We consider multi-objective optimization (MOO) of an unknown vector-valued function in the non-parametric Bayesian optimization (BO) setting, with the aim being to learn points on the Pareto front of the objectives.
On Batch Bayesian Optimization
We present two algorithms for Bayesian optimization in the batch feedback setting, based on Gaussian process upper confidence bound and Thompson sampling approaches, along with frequentist regret guarantees and numerical results.
On Online Learning in Kernelized Markov Decision Processes
We develop algorithms with low regret for learning episodic Markov decision processes based on kernel approximation techniques.
Bayesian Optimization under Heavy-tailed Payoffs
We resolve this gap by developing novel Bayesian optimization algorithms, based on kernel approximation techniques, with regret bounds matching the lower bound in order for the SE kernel.
Online Learning in Kernelized Markov Decision Processes
We consider online learning for minimizing regret in unknown, episodic Markov decision processes (MDPs) with continuous states and actions.
Misspecified Linear Bandits
Regret guarantees for state-of-the-art linear bandit algorithms such as Optimism in the Face of Uncertainty Linear bandit (OFUL) hold under the assumption that the arms expected rewards are perfectly linear in their features.
On Kernelized Multi-armed Bandits
We consider the stochastic bandit problem with a continuous set of arms, with the expected reward function over the arms assumed to be fixed but unknown.
