I’m a PhD student in the CS theory group at Stanford, where I’m very fortunate to be advised by Li‑Yang Tan. Previously,

In the past, my focus was in computational complexity (in particular, circuit lower bounds), but since 2023 I’ve been reorienting towards ML theory in the hopes of helping with AI safety. I’ll be joining the Alignment Research Center in summer 2024.

I write learning notes about various topics within CS theory and math.

Email: vc.lecomte@gmail.com (also vlecomte@stanford.edu)
Twitter: @vclecomte

Research

The composition complexity of majority
 with Prasanna Ramakrishnan and Li-Yang Tan
 CCC 2022 — talk (bonus), slides (bonus)

Sharper bounds on the Fourier concentration of DNFs
 with Li-Yang Tan
 FOCS 2021 — talk, slides

Settling the relationship between Wilber’s bounds for dynamic optimality
 with Omri Weinstein
 ESA 2020 — talk, slides

From discrete-log to lattices: maybe the real lessons were our broken schemes along the way?
 with Alex Bienstock, Allison Bishop, Eli Goldin, and Garrison Grogan
 CFAIL 2020 — talk

The power of adaptivity in source identification with time queries on the path
 with Gergely Ódor and Patrick Thiran
 Theoretical Computer Science, 2022

Forward-checking filtering for nested cardinality constraints: application to an energy cost-aware production planning problem for tissue manufacturing
 with Cyrille Dejemeppe, Olivier Devolder, and Pierre Schaus
 CPAIOR 2016