1 code implementation • 10 Apr 2024 • Ayush Sawarni, Nirjhar Das, Siddharth Barman, Gaurav Sinha
For our batch learning algorithm B-GLinCB, with $\Omega\left( \log{\log T} \right)$ batches, the regret scales as $\tilde{O}(\sqrt{T})$.
no code implementations • 31 Oct 2023 • Daman Arora, Anush Kini, Sayak Ray Chowdhury, Nagarajan Natarajan, Gaurav Sinha, Amit Sharma
Given a query and a document corpus, the information retrieval (IR) task is to output a ranked list of relevant documents.
no code implementations • 8 May 2023 • Ayush Sawarni, Rahul Madhavan, Gaurav Sinha, Siddharth Barman
We study the causal bandit problem that entails identifying a near-optimal intervention from a specified set $A$ of (possibly non-atomic) interventions over a given causal graph.
no code implementations • 1 Oct 2022 • Abhinav Kumar, Gaurav Sinha
In many real-world scenarios, such as gene knockout experiments, targeted interventions are often accompanied by unknown interventions at off-target sites.
no code implementations • 9 Nov 2021 • Vibhor Porwal, Piyush Srivastava, Gaurav Sinha
Our second result shows that this bound is, in fact, within a factor of two of the size of the smallest set of single-node interventions that can orient the MEC.
no code implementations • 1 Nov 2021 • Rahul Madhavan, Aurghya Maiti, Gaurav Sinha, Siddharth Barman
We study Markov Decision Processes (MDP) wherein states correspond to causal graphs that stochastically generate rewards.
no code implementations • 6 Jul 2021 • Aurghya Maiti, Vineet Nair, Gaurav Sinha
First, we propose a simple regret minimization algorithm that takes as input a semi-Markovian causal graph with atomic interventions and possibly unobservable variables, and achieves $\tilde{O}(\sqrt{M/T})$ expected simple regret, where $M$ is dependent on the input CBN and could be very small compared to the number of arms.
no code implementations • 12 Mar 2021 • Gaurav Sinha
We develop efficient randomized algorithms to solve the black-box reconstruction problem for polynomials over finite fields, computable by depth three arithmetic circuits with alternating addition/multiplication gates, such that output gate is an addition gate with in-degree two.
no code implementations • 13 Dec 2020 • Vineet Nair, Vishakha Patil, Gaurav Sinha
If there are no backdoor paths from an intervenable node to the reward node then we propose an algorithm to minimize simple regret that optimally trades-off observations and interventions based on the cost of intervention.
no code implementations • 30 Nov 2019 • Gaurav Sinha, Ayush Chauhan, Aurghya Maiti, Naman Poddar, Pulkit Goel
We study the problem of separating a mixture of distributions, all of which come from interventions on a known causal bayesian network.