Portrait of Ankit Anand

Ankit Anand

Associate Industry Member
Adjunct professor
Senior Research Scientist, Google DeepMind
Website
Google Scholar

Biography

Ankit is currently a Senior Research Scientist at Google DeepMind Montreal and an Associate Industry Member at Mila - Quebec Artificial Intelligence Institute. His research interests lie at the intersection of reasoning and reinforcement learning . He is also interested in applying contemporary AI methods to make advances in Mathematics and Theoretical Computer Science (automated theorem proving and counterexample generation). Recently, he also worked on LearnLM models to develop generative AI models especially trained for pedagogy and teaching applications and how AI could make an impact for equitable Education.

Previously, he completed his Ph.D at IIT Delhi working with Prof. Mausam and Prof. Parag Singla. During his Ph.D, he worked on making symmetry aware A.I algorithms in context of probabilistic graphical models and Monte Carlo Tree Search algorithms.

Publications

Learning to Prove from Synthetic Theorems
Eser Aygün
Zafarali Ahmed
Ankit Anand
Vlad Firoiu
Xavier Glorot
Laurent Orseau
Doina Precup
Shibl Mourad
A major challenge in applying machine learning to automated theorem proving is the scarcity of training data, which is a key ingredient in t… (see more)raining successful deep learning models. To tackle this problem, we propose an approach that relies on training with synthetic theorems, generated from a set of axioms. We show that such theorems can be used to train an automated prover and that the learned prover transfers successfully to human-generated theorems. We demonstrate that a prover trained exclusively on synthetic theorems can solve a substantial fraction of problems in TPTP, a benchmark dataset that is used to compare state-of-the-art heuristic provers. Our approach outperforms a model trained on human-generated problems in most axiom sets, thereby showing the promise of using synthetic data for this task.
2020-06-19
ArXiv (preprint)
arxiv.org
arxiv.org