Debabrota Basu

Efficient Active Auditing of Multi-Group Fairness with Bias Probes

Ayoub Ajarra, Debabrota Basu

Over the past decade, Machine Learning (ML) has been trained under dual objectives: minimizing prediction error via Empirical Risk Minimization (ERM) while controlling unfairness b…

Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts

Udvas Das, Waris Radji, Debabrota Basu +1

We consider a variant of the linear contextual stochastic multi-armed bandits, where the learner must provide recommendations to a group of users, each having its personalized pref…

Sequential Membership Inference Attacks

Thomas Michel, Debabrota Basu, Emilie Kaufmann

Modern AI models are not static. They go through multiple updates in their lifecycles. We propose to design Sequential Membership Inference (SeMI) attacks leading to tighter privac…

Auditing Fairness under Model Updates: Fundamental Complexity and Property-Preserving Updates

Ayoub Ajarra, Debabrota Basu

As machine learning models become increasingly embedded in societal infrastructure, auditing them for bias is of growing importance. However, in real-world deployments, auditing is…

Performative Policy Gradient: Optimality in Performative Reinforcement Learning

Debabrota Basu, Udvas Das, Brahim Driss +1

Post-deployment machine learning algorithms often influence the environments they act in, and thus shift the underlying dynamics that the standard reinforcement learning (RL) metho…

Dimension Agnostic Testing of Survey Data Credibility through the Lens of Regression

Debabrota Basu, Sourav Chakraborty, Debarshi Chanda +3

Assessing whether a sample survey credibly represents the population is a critical question for ensuring the validity of downstream research. Generally, this problem reduces to est…

FraPPE: Fast and Efficient Preference-based Pure Exploration

Udvas Das, Apurv Shukla, Debabrota Basu

Preference-based Pure Exploration (PrePEx) aims to identify with a given confidence level the set of Pareto optimal arms in a vector-valued (aka multi-objective) bandit, where the…

Lagrangian-based Equilibrium Propagation: generalisation to arbitrary boundary conditions & equivalence with Hamiltonian Echo Learning

Guillaume Pourcel, Debabrota Basu, Maxence Ernoult +1

Equilibrium Propagation (EP) is a learning algorithm for training Energy-based Models (EBMs) on static inputs which leverages the variational description of their fixed points. Ext…

Sublinear Algorithms for Wasserstein and Total Variation Distances: Applications to Fairness and Privacy Auditing

Debabrota Basu, Debarshi Chanda

Resource-efficiently computing representations of probability distributions and the distances between them while only having access to the samples is a fundamental and useful probl…

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret

Emilio Jorge, Christos Dimitrakakis, Debabrota Basu

Common assumptions, like linear or RKHS models, and Gaussian or log-concave posteriors over the models, do not explain practical success of RL across a wider range of distributions…

Dynamical-VAE-based Hindsight to Learn the Causal Dynamics of Factored-POMDPs

Chao Han, Debabrota Basu, Michael Mangan +2

Learning representations of underlying environmental dynamics from partial observations is a critical challenge in machine learning. In the context of Partially Observable Markov D…

Active Fourier Auditor for Estimating Distributional Properties of ML Models

Ayoub Ajarra, Bishwamittra Ghosh, Debabrota Basu

With the pervasive deployment of Machine Learning (ML) models in real-world applications, verifying and auditing properties of ML models have become a central concern. In this work…

Testing Credibility of Public and Private Surveys through the Lens of Regression

Debabrota Basu, Sourav Chakraborty, Debarshi Chanda +3

Testing whether a sample survey is a credible representation of the population is an important question to ensure the validity of any downstream research. While this problem, in ge…

Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints

Udvas Das, Debabrota Basu

Pure exploration in bandits formalises multiple real-world problems, such as tuning hyper-parameters or conducting user studies to test a set of items, where different safety, reso…

When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning

Naheed Anjum Arafat, Debabrota Basu, Yulia Gel +1

Capitalizing on the intuitive premise that shape characteristics are more robust to perturbations, we bridge adversarial graph learning with the emerging tools from computational t…

Augmented Bayesian Policy Search

Mahdi Kallel, Debabrota Basu, Riad Akrour +1

Deterministic policies are often preferred over stochastic ones when implemented on physical systems. They can prevent erratic and harmful behaviors while being easier to implement…

History-Aware and Dynamic Client Contribution in Federated Learning

Bishwamittra Ghosh, Debabrota Basu, Fu Huazhu +6

Federated Learning (FL) is a collaborative machine learning (ML) approach, where multiple clients participate in training an ML model without exposing their private data. Fair and…

Some Targets Are Harder to Identify than Others: Quantifying the Target-dependent Membership Leakage

Achraf Azize, Debabrota Basu

In a Membership Inference (MI) game, an attacker tries to infer whether a target point was included or not in the input of an algorithm. Existing works show that some target points…