activity
20092023
most citedProvably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

261 citations · 1.4k across the 45 of their papers we have counts for

collaborators

59 papers

cs.CL2023★ 52 cited

Textbooks Are All You Need II: phi-1.5 technical report

Yuanzhi Li, Sébastien Bubeck, Ronen Eldan +3

We continue the investigation into the power of smaller Transformer-based language models as initiated by \textbf{TinyStories} -- a 10 million parameter model that can produce cohe…

cs.LG2022

Learning threshold neurons via the "edge of stability"

Kwangjun Ahn, Sébastien Bubeck, Sinho Chewi +3

Existing analyses of neural network training often operate under the unrealistic assumption of an extremely small learning rate. This lies in stark contrast to practical wisdom and…

cs.DS2022★ 2 cited

The Randomized -Server Conjecture is False!

Sébastien Bubeck, Christian Coester, Yuval Rabani

We prove a few new lower bounds on the randomized competitive ratio for the -server problem and other related problems, resolving some long-standing conjectures. In particular,…

math.OC2022

On the complexity of finding stationary points of smooth functions in one dimension

Sinho Chewi, Sébastien Bubeck, Adil Salim

We characterize the query complexity of finding stationary points of one-dimensional non-convex but smooth functions. We consider four settings, based on whether the algorithms und…

cs.DS2022

Shortest Paths without a Map, but with an Entropic Regularizer

Sébastien Bubeck, Christian Coester, Yuval Rabani

In a 1989 paper titled "shortest paths without a map", Papadimitriou and Yannakakis introduced an online model of searching in a weighted layered graph for a target node, while att…

quant-ph2020★ 7 cited

Entanglement is Necessary for Optimal Quantum Property Testing

Sebastien Bubeck, Sitan Chen, Jerry Li

There has been a surge of progress in recent years in developing algorithms for testing and learning quantum states that achieve optimal copy complexity. Unfortunately, they requir…