320 citations · 1.4k across the 33 of their papers we have counts for
34 papers
Transformer Models for Type Inference in the Simply Typed Lambda Calculus: A Case Study in Deep Learning for Code
Brando Miranda, Avi Shinnar, Vasily Pestun +1
Despite a growing body of work at the intersection of deep learning and formal languages, there has been relatively little systematic exploration of transformer models for reasonin…
Formalization of a Stochastic Approximation Theorem
Koundinya Vajjha, Barry Trager, Avraham Shinnar +1
Stochastic approximation algorithms are iterative procedures which are used to approximate a target value in an environment where the target is unknown and direct observations are…
CertRL: Formalizing Convergence Proofs for Value and Policy Iteration in Coq
Koundinya Vajjha, Avraham Shinnar, Vasily Pestun +2
Reinforcement learning algorithms solve sequential decision-making problems in probabilistic environments by optimizing for long-term reward. The desire to use reinforcement learni…
Lax matrices from antidominantly shifted Yangians and quantum affine algebras: A-type
Rouven Frassek, Vasily Pestun, Alexander Tsymbaliuk
We construct a family of rational and trigonometric Lax matrices parametrized by -valued divisors on . To this end, we study the shifted Drin…
Super instanton counting and localization
Taro Kimura, Vasily Pestun
We study the super instanton solution in the gauge theory with U gauge group. Based on the ADHM construction generalized to the supergroup theory, we derive the ins…
Twisted reduction of quiver W-algebras
Taro Kimura, Vasily Pestun
We consider the -twisted Nekrasov-Shatashvili limit (NS limit) of 5d (K-theoretic) and 6d (elliptic) quiver gauge theory, where one of the multiplicative equivariant paramet…