Sébastien Bubeck

Orcid: 0000-0001-9122-4410

According to our database1, Sébastien Bubeck authored at least 111 papers between 2007 and 2024.

Collaborative distances:
  • Dijkstra number2 of three.
  • Erdős number3 of two.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
How to Trap a Gradient Flow.
SIAM J. Comput., 2024

Small Language Models for Application Interactions: A Case Study.
CoRR, 2024

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.
CoRR, 2024

How to Fine-Tune Vision Models with SGD.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
A Universal Law of Robustness via Isoperimetry.
J. ACM, April, 2023

First-Order Bayesian Regret Analysis of Thompson Sampling.
IEEE Trans. Inf. Theory, March, 2023

TinyGSM: achieving >80% on GSM8k with small language models.
CoRR, 2023

Positional Description Matters for Transformers Arithmetic.
CoRR, 2023

Textbooks Are All You Need II: phi-1.5 technical report.
CoRR, 2023

Textbooks Are All You Need.
CoRR, 2023

Sparks of Artificial General Intelligence: Early experiments with GPT-4.
CoRR, 2023

The Randomized k-Server Conjecture Is False!
Proceedings of the 55th Annual ACM Symposium on Theory of Computing, 2023

Learning threshold neurons via edge of stability.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On the complexity of finding stationary points of smooth functions in one dimension.
Proceedings of the International Conference on Algorithmic Learning Theory, 2023

AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation.
Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2022
AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers.
CoRR, 2022

Unveiling Transformers with LEGO: a synthetic reasoning task.
CoRR, 2022

LiteTransformerSearch: Training-free On-device Search for Efficient Autoregressive Language Models.
CoRR, 2022

Data Augmentation as Feature Manipulation: a story of desert cows and grass cows.
CoRR, 2022

LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Data Augmentation as Feature Manipulation.
Proceedings of the International Conference on Machine Learning, 2022

Shortest Paths without a Map, but with an Entropic Regularizer.
Proceedings of the 63rd IEEE Annual Symposium on Foundations of Computer Science, 2022

2021
Metrical Task Systems on Trees via Mirror Descent and Unfair Gluing.
SIAM J. Comput., 2021

Kernel-based Methods for Bandit Convex Optimization.
J. ACM, 2021

FEAR: A Simple Lightweight Method to Rank Architectures.
CoRR, 2021

Online Multiserver Convex Chasing and Optimization.
Proceedings of the 2021 ACM-SIAM Symposium on Discrete Algorithms, 2021

A single gradient step finds adversarial examples on random two-layers neural networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Adversarial Examples in Multi-Layer Random ReLU Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Metrical Service Systems with Transformations.
Proceedings of the 12th Innovations in Theoretical Computer Science Conference, 2021

A Law of Robustness for Two-Layers Neural Networks.
Proceedings of the Conference on Learning Theory, 2021

Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions.
Proceedings of the Conference on Learning Theory, 2021

2020
Network size and weights size for memorization with two-layers neural networks.
CoRR, 2020

Chasing Nested Convex Bodies Nearly Optimally.
Proceedings of the 2020 ACM-SIAM Symposium on Discrete Algorithms, 2020

Network size and size of the weights in memorization with two-layers neural networks.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Online Learning for Active Cache Synchronization.
Proceedings of the 37th International Conference on Machine Learning, 2020

Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization.
Proceedings of the 37th International Conference on Machine Learning, 2020

Entanglement is Necessary for Optimal Quantum Property Testing.
Proceedings of the 61st IEEE Annual Symposium on Foundations of Computer Science, 2020

Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without.
Proceedings of the Conference on Learning Theory, 2020

Coordination without communication: optimal regret in two players multi-armed bandits.
Proceedings of the Conference on Learning Theory, 2020

Parametrized Metrical Task Systems.
Proceedings of the Approximation, 2020

2019
The Entropic Barrier: Exponential Families, Log-Concave Geometry, and Self-Concordance.
Math. Oper. Res., 2019

Optimal Convergence Rates for Convex Distributed Optimization in Networks.
J. Mach. Learn. Res., 2019

Multi-scale Online Learning: Theory and Applications to Online Auctions and Pricing.
J. Mach. Learn. Res., 2019

First-Order Regret Analysis of Thompson Sampling.
CoRR, 2019

Competitively chasing convex bodies.
Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing, 2019

A Nearly-Linear Bound for Chasing Nested Convex Bodies.
Proceedings of the Thirtieth Annual ACM-SIAM Symposium on Discrete Algorithms, 2019

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Complexity of Highly Parallel Non-Smooth Convex Optimization.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Adversarial examples from computational constraints.
Proceedings of the 36th International Conference on Machine Learning, 2019

Near Optimal Methods for Minimizing Convex Functions with Lipschitz $p$-th Derivatives.
Proceedings of the Conference on Learning Theory, 2019

Improved Path-length Regret Bounds for Bandits.
Proceedings of the Conference on Learning Theory, 2019

Near-optimal method for highly smooth convex optimization.
Proceedings of the Conference on Learning Theory, 2019

2018
Sampling from a Log-Concave Distribution with Projected Langevin Monte Carlo.
Discret. Comput. Geom., 2018

Adversarial Examples from Cryptographic Pseudo-Random Generators.
CoRR, 2018

Chasing Nested Convex Bodies Nearly Optimally.
CoRR, 2018

Adversarial examples from computational constraints.
CoRR, 2018

k-server via multiscale entropic regularization.
Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing, 2018

An homotopy method for l<sub>p</sub> regression provably beyond self-concordance and in input-sparsity time.
Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing, 2018

Optimal Algorithms for Non-Smooth Distributed Optimization in Networks.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Is Q-Learning Provably Efficient?
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits.
Proceedings of the 35th International Conference on Machine Learning, 2018

Conference on Learning Theory 2018: Preface.
Proceedings of the Conference On Learning Theory, 2018

Sparsity, variance and curvature in multi-armed bandits.
Proceedings of the Algorithmic Learning Theory, 2018

2017
Finding Adam in random growing trees.
Random Struct. Algorithms, 2017

Local max-cut in smoothed polynomial time.
Proceedings of the 49th Annual ACM SIGACT Symposium on Theory of Computing, 2017

Online Auctions and Multi-scale Online Learning.
Proceedings of the 2017 ACM Conference on Economics and Computation, 2017

Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks.
Proceedings of the 34th International Conference on Machine Learning, 2017

2016
Testing for high-dimensional geometry in random graphs.
Random Struct. Algorithms, 2016

On the Local Profiles of Trees.
J. Graph Theory, 2016

Basic models and questions in statistical network analysis.
CoRR, 2016

Black-box Optimization with a Politician.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Multi-scale exploration of convex functions and bandit convex optimization.
Proceedings of the 29th Conference on Learning Theory, 2016

2015
On the Influence of the Seed Graph in the Preferential Attachment Model.
IEEE Trans. Netw. Sci. Eng., 2015

Exceptional rotations of random graphs: a VC theory.
J. Mach. Learn. Res., 2015

Convex Optimization: Algorithms and Complexity.
Found. Trends Mach. Learn., 2015

A geometric alternative to Nesterov's accelerated gradient descent.
CoRR, 2015

Entropic CLT and phase transition in high-dimensional Wishart matrices.
CoRR, 2015

Finite-Time Analysis of Projected Langevin Monte Carlo.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

The entropic barrier: a simple and optimal universal self-concordant barrier.
Proceedings of The 28th Conference on Learning Theory, 2015

Bandit Convex Optimization: \(\sqrt{T}\) Regret in One Dimension.
Proceedings of The 28th Conference on Learning Theory, 2015

2014
Regret in Online Combinatorial Optimization.
Math. Oper. Res., 2014

From trees to seeds: on the inference of the seed from large trees in the uniform attachment model.
CoRR, 2014

Theory of Convex Optimization for Machine Learning.
CoRR, 2014

Most Correlated Arms Identification.
Proceedings of The 27th Conference on Learning Theory, 2014

lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits.
Proceedings of The 27th Conference on Learning Theory, 2014

2013
Bandits With Heavy Tail.
IEEE Trans. Inf. Theory, 2013

Optimal discovery with probabilistic expert advice: finite time analysis and macroscopic optimality.
J. Mach. Learn. Res., 2013

A note on the Bayesian regret of Thompson Sampling with an arbitrary prior
CoRR, 2013

On Finding the Largest Mean Among Many.
CoRR, 2013

Prior-free and prior-dependent regret bounds for Thompson Sampling.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Multiple Identifications in Multi-Armed Bandits.
Proceedings of the 30th International Conference on Machine Learning, 2013

Bounded regret in stochastic multi-armed bandits.
Proceedings of the COLT 2013, 2013

2012
The Best of Both Worlds: Stochastic and Adversarial Bandits.
Proceedings of the COLT 2012, 2012

Towards Minimax Policies for Online Linear Optimization with Bandit Feedback.
Proceedings of the COLT 2012, 2012

Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems.
Found. Trends Mach. Learn., 2012

Optimal discovery with probabilistic expert advice.
Proceedings of the 51th IEEE Conference on Decision and Control, 2012

2011
Pure exploration in finitely-armed and continuous-armed bandits.
Theor. Comput. Sci., 2011

<i>X</i>-Armed Bandits.
J. Mach. Learn. Res., 2011

Minimax Policies for Combinatorial Prediction Games.
Proceedings of the COLT 2011, 2011

Multi-Bandit Best Arm Identification.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

Lipschitz Bandits without the Lipschitz Constant.
Proceedings of the Algorithmic Learning Theory - 22nd International Conference, 2011

2010
Regret Bounds and Minimax Policies under Partial Monitoring.
J. Mach. Learn. Res., 2010

X-Armed Bandits
CoRR, 2010

Open Loop Optimistic Planning.
Proceedings of the COLT 2010, 2010

Best Arm Identification in Multi-Armed Bandits.
Proceedings of the COLT 2010, 2010

2009
Nearest Neighbor Clustering: A Baseline Method for Consistent Clustering with Arbitrary Objective Functions.
J. Mach. Learn. Res., 2009

Minimax Policies for Adversarial and Stochastic Bandits.
Proceedings of the COLT 2009, 2009

Pure Exploration in Multi-armed Bandits Problems.
Proceedings of the Algorithmic Learning Theory, 20th International Conference, 2009

2008
Pure Exploration for Multi-Armed Bandit Problems
CoRR, 2008

Online Optimization in X-Armed Bandits.
Proceedings of the Advances in Neural Information Processing Systems 21, 2008

2007
Consistent Minimization of Clustering Objective Functions.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007


  Loading...