Search Results for author:
Found 38 papers, 12 papers with code
Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret
First, we show that the Posterior Sampling-based RL (PSRL) yields sublinear regret if the data distributions satisfy LSI under some mild additional assumptions.
Preference-based Pure Exploration
First, to quantify the impact of preferences, we derive a novel lower bound on sample complexity for identifying the most preferred policy with a confidence level $1-\delta$.
Dynamical-VAE-based Hindsight to Learn the Causal Dynamics of Factored-POMDPs
Learning representations of underlying environmental dynamics from partial observations is a critical challenge in machine learning.
Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints
First, we propose a Lagrangian relaxation of the sample complexity lower bound for pure exploration under constraints.
Active Fourier Auditor for Estimating Distributional Properties of ML Models
For this purpose, we develop a new framework that quantifies different properties in terms of the Fourier coefficients of the ML model under audit but does not parametrically reconstruct it.
Testing Credibility of Public and Private Surveys through the Lens of Regression
We prove the theoretical correctness of our algorithms while trying to reduce the sample complexity for both public and private surveys.
When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning
We introduce the concept of witness complex to adversarial analysis on graphs, which allows us to focus only on the salient shape characteristics of graphs, yielded by the subset of the most essential nodes (i. e., landmarks), with minimal loss of topological information on the whole graph.
Augmented Bayesian Policy Search
The resulting algorithm combines the convenience of the direct policy search with the scalability of reinforcement learning.
Differentially Private Best-Arm Identification
First, to quantify the cost of privacy, we derive lower bounds on the sample complexity of any $\delta$-correct BAI algorithm satisfying $\epsilon$-global DP or $\epsilon$-local DP.
FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits
High dimensional sparse linear bandits serve as an efficient model for sequential decision-making problems (e. g. personalized medicine), where high dimensional features (e. g. genomic data) on the users are available, but only a small subset of them are relevant.
Don't Forget What I did?: Assessing Client Contributions in Federated Learning
Additionally, to assess client contribution under limited computational budget, we propose a scheduling procedure that considers a two-sided fairness criteria to perform expensive Shapley value computation only in a subset of training epochs.
How Much Does Each Datapoint Leak Your Privacy? Quantifying the Per-datum Membership Leakage
We study the per-datum Membership Inference Attacks (MIAs), where an attacker aims to infer whether a fixed target datum has been included in the input dataset of an algorithm and thus, violates privacy.
How does Your RL Agent Explore? An Optimal Transport Analysis of Occupancy Measure Trajectories
Using an optimal transport-based metric, we measure the length of the paths induced by the policy sequence yielded by an RL algorithm between an initial policy and a final optimal policy.
CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption
In this setting, accommodating potentially unbounded corruptions, we establish a problem-dependent lower bound on regret for a given family of arm distributions.
Concentrated Differential Privacy for Bandits
Next, we complement our regret upper bounds with the first minimax lower bounds on the regret of bandits with zCDP.
Pure Exploration in Bandits with Linear Constraints
Both these algorithms try to track an optimal allocation based on the lower bound and computed by a weighted projection onto the boundary of a normal cone.
From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning
We study differentially private (DP) machine learning algorithms as instances of noisy fixed-point iterations, in order to derive privacy and utility results from this well-studied framework.
Stochastic Online Instrumental Variable Regression: Regrets for Endogeneity and Bandit Feedback
Endogeneity, i. e. the dependence of noise and covariates, is a common phenomenon in real data due to omitted variables, strategic behaviours, measurement errors etc.
Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer
Then, we propose a generic two-stage algorithm, MLEMTRL, to address the MTRL problem in discrete and continuous settings.
Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public Data
We study design of black-box model extraction attacks that can send minimal number of queries from a publicly available dataset to a target ML model through a predictive API with an aim to create an informative and distributionally equivalent replica of the target.
Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning
Our regret bound is order-optimal with respect to $H$ and $K$.
When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits
First, we prove the minimax and problem-dependent regret lower bounds for stochastic and linear bandits that quantify the hardness of bandits with $\epsilon$-global DP.
How Biased are Your Features?: Computing Fairness Influence Functions with Global Sensitivity Analysis
In this paper, we aim to quantify the influence of different features in a dataset on the bias of a classifier.
SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics
In SAAC, the adversary aims to break the safety constraint while the RL agent aims to maximize the constrained value function given the adversary's policy.
Risk-Sensitive Bayesian Games for Multi-Agent Reinforcement Learning under Policy Uncertainty
In existing literature, the risk in stochastic games has been studied in terms of the inherent uncertainty evoked by the variability of transitions and actions.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithm
We study the corrupted bandit problem, i. e. a stochastic multi-armed bandit problem with $k$ unknown reward distributions, which are heavy-tailed and corrupted by a history-independent adversary or Nature.
Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-Fidelity Feedback
In black-box optimization problems, we aim to maximize an unknown objective function, where the function is only accessible through feedbacks of an evaluation or simulation oracle.
Algorithmic Fairness Verification with Graphical Models
In recent years, machine learning (ML) algorithms have been deployed in safety-critical and high-stake decision-making, where the fairness of algorithms is of paramount importance.
On Meritocracy in Optimal Set Selection
Typically, merit is defined with respect to some intrinsic measure of worth.
SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning
In this paper, we consider risk-sensitive sequential decision-making in Reinforcement Learning (RL).
Justicia: A Stochastic SAT Approach to Formally Verify Fairness
We instantiate Justicia on multiple classification and bias mitigation algorithms, and datasets to verify different fairness metrics, such as disparate impact, statistical parity, and equalized odds.
Differential Privacy at Risk: Bridging Randomness and Privacy Budget
We also propose a cost model that bridges the gap between the privacy level and the compensation budget estimated by a GDPR compliant business entity.
Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning
Bayesian reinforcement learning (BRL) offers a decision-theoretic solution for reinforcement learning.
Near-optimal Bayesian Solution For Unknown Discrete Markov Decision Process
We derive the first polynomial time Bayesian algorithm, BUCRL{} that achieves up to logarithm factors, a regret (i. e the difference between the accumulated rewards of the optimal policy and our algorithm) of the optimal order $\tilde{\mathcal{O}}(\sqrt{DSAT})$.
Differential Privacy for Multi-armed Bandits: What Is It and What Is Its Cost?
We derive and contrast lower bounds on the regret of bandit algorithms satisfying these definitions.
Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities
We study model-based reinforcement learning in an unknown finite communicating Markov decision process.
Model-based Reinforcement Learning
reinforcement-learning
+2
Bayesian Reinforcement Learning via Deep, Sparse Sampling
We address the problem of Bayesian reinforcement learning using efficient model-based online planning.
BelMan: Bayesian Bandits on the Belief--Reward Manifold
BelMan alternates \emph{information projection} and \emph{reverse information projection}, i. e., projection of the pseudobelief-reward onto beliefs-rewards to choose the arm to play, and projection of the resulting beliefs-rewards onto the pseudobelief-reward.
