Search Results for author:
Found 40 papers, 12 papers with code
Robust Multi-Objective Controlled Decoding of Large Language Models
Test-time alignment of Large Language Models (LLMs) to human preferences offers a flexible way to generate responses aligned to diverse objectives without extensive retraining of LLMs.
This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs
Mixture of large language model (LLMs) Agents (MoA) architectures achieve state-of-the-art performance on prominent benchmarks like AlpacaEval 2. 0 by leveraging the collaboration of multiple LLMs at inference time.
Mean-Field Bayesian Optimisation
We address the problem of optimising the average payoff for a large number of cooperating agents, where the payoff function is unknown and treated as a black box.
No-Regret Linear Bandits under Gap-Adjusted Misspecification
It achieves a near-optimal $O(\sqrt{T})$ regret for problems that the best-known regret is almost linear in time horizon $T$.
Sample-efficient Bayesian Optimisation Using Known Invariances
We derive a bound on the maximum information gain of these invariant kernels, and provide novel upper and lower bounds on the number of observations required for invariance-aware BO algorithms to achieve $\epsilon$-optimality.
Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
We theoretically analyse the convergence of NS-DPO in the offline setting, providing upper bounds on the estimation error caused by non-stationary preferences.
Adversarially Robust Decision Transformer
Decision Transformer (DT), as one of the representative Reinforcement Learning via Supervised Learning (RvS) methods, has achieved strong performance in offline learning tasks by leveraging the powerful Transformer architecture for sequential decision-making.
Group Robust Preference Optimization in Reward-free RLHF
Our approach builds upon reward-free direct preference optimization methods, but unlike previous approaches, it seeks a robust policy which maximizes the worst-case group performance.
PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks
Our paper offers a new approach to certify the performance of machine learning models in the presence of adversarial attacks with population level risk guarantees.
Sample Efficient Preference Alignment in LLMs via Active Exploration
For many applications of preference alignment, the cost of acquiring human feedback can be substantial.
REDUCR: Robust Data Downsampling Using Class Priority Reweighting
REDUCR reduces the training data while preserving worst-class generalization performance.
Robust Best-arm Identification in Linear Bandits
To this end, we present an instance-dependent lower bound for the robust best-arm identification problem with linear rewards.
Distributionally Robust Model-based Reinforcement Learning with Large State Spaces
Three major challenges in reinforcement learning are the complex dynamical systems with large state spaces, the costly data acquisition processes, and the deviation of real-world dynamics from the training environment deployment.
Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning
Many applications, e. g., in shared mobility, require coordinating a large number of agents.
Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning
A practical challenge in reinforcement learning are combinatorial action spaces that make planning computationally demanding.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Near-optimal Policy Identification in Active Reinforcement Learning
Many real-world reinforcement learning tasks require control of complex dynamical systems that involve both costly data acquisition processes and large state spaces.
Movement Penalized Bayesian Optimization with Application to Wind Energy Systems
Contextual Bayesian optimization (CBO) is a powerful framework for sequential decision-making given side information, with important applications, e. g., in wind energy systems.
Graph Neural Network Bandits
By establishing a novel connection between such kernels and the graph neural tangent kernel (GNTK), we introduce the first GNN confidence bound and use it to design a phased-elimination algorithm with sublinear regret.
A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits
We consider the sequential optimization of an unknown, continuous, and expensive to evaluate reward function, from noisy and adversarially corrupted observed rewards.
Misspecified Gaussian Process Bandit Optimization
Instead, we introduce a \emph{misspecified} kernelized bandit setting where the unknown function can be $\epsilon$--uniformly approximated by a function with a bounded norm in some Reproducing Kernel Hilbert Space (RKHS).
Risk-averse Heteroscedastic Bayesian Optimization
We generalize BO to trade mean and input-dependent variance of the objective, both of which we assume to be unknown a priori.
Contextual Games: Multi-Agent Learning with Side Information
We formulate the novel class of contextual games, a type of repeated games driven by contextual information at each round.
Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning
Learning in multi-agent systems is highly challenging due to several factors including the non-stationarity introduced by agents' interactions and the combinatorial nature of their state and action spaces.
Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning
In real-world tasks, reinforcement learning (RL) agents frequently encounter situations that are not present during training time.
Deep Reinforcement Learning
Model-based Reinforcement Learning
+2
Cost-Efficient Online Hyperparameter Optimization
Recent work on hyperparameters optimization (HPO) has shown the possibility of training certain hyperparameters together with regular parameters.
Learning to Play Sequential Games versus Unknown Opponents
We consider a repeated sequential game between a learner, who plays first, and an opponent who responds to the chosen action.
Stochastic Linear Bandits Robust to Adversarial Attacks
We consider a stochastic linear bandit problem in which the rewards are not only subject to random noise, but also adversarial attacks subject to a suitable budget $C$ (i. e., an upper bound on the sum of corruption magnitudes across the time horizon).
Corruption-Tolerant Gaussian Process Bandit Optimization
We consider the problem of optimizing an unknown (typically non-convex) function with a bounded norm in some Reproducing Kernel Hilbert Space (RKHS), based on noisy bandit feedback.
Mixed Strategies for Robust Optimization of Unknown Objectives
We consider robust optimization problems, where the goal is to optimize an unknown objective function against the worst-case realization of an uncertain parameter.
Distributionally Robust Bayesian Optimization
Attaining such robustness is the goal of distributionally robust optimization, which seeks a solution to an optimization problem that is worst-case robust under a specified distributional shift of an uncontrolled covariate.
No-Regret Learning in Unknown Games with Correlated Payoffs
We consider the problem of learning to play a repeated multi-agent game with an unknown reward function.
Adversarially Robust Optimization with Gaussian Processes
In this paper, we consider the problem of Gaussian process (GP) optimization with an added robustness requirement: The returned point may be perturbed by an adversary, and we require the function value to remain as high as possible even after this perturbation.
Robust Maximization of Non-Submodular Objectives
In this work, we present a new algorithm Oblivious-Greedy and prove the first constant-factor approximation guarantees for a wider class of non-submodular objectives.
High-Dimensional Bayesian Optimization via Additive Models with Overlapping Groups
In this paper, we consider the approach of Kandasamy et al. (2015), in which the high-dimensional function decomposes as a sum of lower-dimensional functions on subsets of the underlying variables.
Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach
We study the classical problem of maximizing a monotone submodular function subject to a cardinality constraint k, with two additional twists: (i) elements arrive in a streaming fashion, and (ii) m items from the algorithm's memory are removed after the stream is finished.
Robust Submodular Maximization: A Non-Uniform Partitioning Approach
We study the problem of maximizing a monotone submodular function subject to a cardinality constraint $k$, with the added twist that a number of items $\tau$ from the returned set may be removed.
Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation
We present a new algorithm, truncated variance reduction (TruVaR), that treats Bayesian optimization (BO) and level-set estimation (LSE) with Gaussian processes in a unified fashion.
Time-Varying Gaussian Process Bandit Optimization
We illustrate the performance of the algorithms on both synthetic and real data, and we find the gradual forgetting of TV-GP-UCB to perform favorably compared to the sharp resetting of R-GP-UCB.
Learning-based Compressive Subsampling
In this paper, we instead take a principled learning-based approach in which a \emph{fixed} index set is chosen based on a set of training signals $\mathbf{x}_1,\dotsc,\mathbf{x}_m$.
Near-Optimally Teaching the Crowd to Classify
How should we present training examples to learners to teach them classification rules?
