Ronen Eldan

CoRR, 2024

2023

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

[BibT_eX]

[DOI]

CoRR, 2023

Positional Description Matters for Transformers Arithmetic.

[BibT_eX]

[DOI]

CoRR, 2023

Fast relaxation of the random field Ising dynamics.

[BibT_eX]

[DOI]

CoRR, 2023

Who's Harry Potter? Approximate Unlearning in LLMs.

[BibT_eX]

[DOI]

Caio César Teodoro Mendes

Mark Russinovich

CoRR, 2023

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

[BibT_eX]

[DOI]

CoRR, 2023

Textbooks Are All You Need.

[BibT_eX]

[DOI]

Suriya Gunasekar

Yi Zhang

Jyoti Aneja

CoRR, 2023

TinyStories: How Small Can Language Models Be and Still Speak Coherent English?

[BibT_eX]

[DOI]

Yuanzhi Li

CoRR, 2023

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

[BibT_eX]

[DOI]

CoRR, 2023

An Optimal "It Ain't Over Till It's Over" Theorem.

[BibT_eX]

[DOI]

Avi Wigderson

Pei Wu

Proceedings of the 55th Annual ACM Symposium on Theory of Computing, 2023

Noise Stability on the Boolean Hypercube via a Renormalized Brownian Motion.

[BibT_eX]

[DOI]

Prasad Raghavendra

Proceedings of the 55th Annual ACM Symposium on Theory of Computing, 2023

2022

Second-Order Bounds on Correlations Between Increasing Families.

[BibT_eX]

[DOI]

Comb., December, 2022

Community detection and percolation of information in a geometric setting.

[BibT_eX]

[DOI]

Hester Pieters

Comb. Probab. Comput., 2022

Hit-and-run mixing via localization schemes.

[BibT_eX]

[DOI]

Yuansi Chen

CoRR, 2022

Unveiling Transformers with LEGO: a synthetic reasoning task.

[BibT_eX]

[DOI]

CoRR, 2022

Isoperimetric Inequalities Made Simpler.

[BibT_eX]

[DOI]

CoRR, 2022

Localization Schemes: A Framework for Proving Mixing Bounds for Markov Chains.

[BibT_eX]

[DOI]

Yuansi Chen

CoRR, 2022

Localization Schemes: A Framework for Proving Mixing Bounds for Markov Chains (extended abstract).

[BibT_eX]

[DOI]

Yuansi Chen

Proceedings of the 63rd IEEE Annual Symposium on Foundations of Computer Science, 2022

2021

Kernel-based Methods for Bandit Convex Optimization.

[BibT_eX]

[DOI]

Yin Tat Lee

J. ACM, 2021

Non-asymptotic approximations of neural networks by Gaussian processes.

[BibT_eX]

[DOI]

Tselil Schramm

Proceedings of the Conference on Learning Theory, 2021

2020

Reduction From Non-Unique Games To Boolean Unique Games.

[BibT_eX]

[DOI]

Dana Moshkovitz

Electron. Colloquium Comput. Complex., 2020

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

[BibT_eX]

[DOI]

CoRR, 2020

Concentration on the Boolean hypercube via pathwise stochastic analysis.

[BibT_eX]

[DOI]

Renan Gross

Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing, 2020

Network size and size of the weights in memorization with two-layers neural networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

The Entropic Barrier: Exponential Families, Log-Concave Geometry, and Self-Concordance.

[BibT_eX]

[DOI]

Math. Oper. Res., 2019

Stability of Talagrand's influence inequality.

[BibT_eX]

[DOI]

Renan Gross

CoRR, 2019

Krivine diffusions attain the Goemans-Williamson approximation ratio.

[BibT_eX]

[DOI]

Assaf Naor

CoRR, 2019

Stability of the Shannon-Stam inequality via the Föllmer process.

[BibT_eX]

[DOI]

CoRR, 2019

Depth Separations in Neural Networks: What is Actually Being Separated?

[BibT_eX]

[DOI]

Itay Safran

Ohad Shamir

Proceedings of the Conference on Learning Theory, 2019

2018

Efficient algorithms for discrepancy minimization in convex sets.

[BibT_eX]

[DOI]

Mohit Singh

Random Struct. Algorithms, 2018

Sampling from a Log-Concave Distribution with Projected Langevin Monte Carlo.

[BibT_eX]

[DOI]

Joseph Lehec

Discret. Comput. Geom., 2018

2017

Braess's paradox for the spectral gap in random graphs and delocalization of eigenvectors.

[BibT_eX]

[DOI]

Miklós Z. Rácz

Tselil Schramm

Random Struct. Algorithms, 2017

Exponential random graphs behave like mixtures of stochastic block models.

[BibT_eX]

[DOI]

Renan Gross

CoRR, 2017

2016

Testing for high-dimensional geometry in random graphs.

[BibT_eX]

[DOI]

Random Struct. Algorithms, 2016

Information and dimensionality of anisotropic random geometric graphs.

[BibT_eX]

[DOI]

CoRR, 2016

The Power of Depth for Feedforward Neural Networks.

[BibT_eX]

[DOI]

Ohad Shamir

Proceedings of the 29th Conference on Learning Theory, 2016

Multi-scale exploration of convex functions and bandit convex optimization.

[BibT_eX]

[DOI]

Proceedings of the 29th Conference on Learning Theory, 2016

2015

Bandit Smooth Convex Optimization: Improving the Bias-Variance Tradeoff.

[BibT_eX]

[DOI]

Ofer Dekel

Tomer Koren

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Finite-Time Analysis of Projected Langevin Monte Carlo.

[BibT_eX]

[DOI]

Joseph Lehec

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Talagrand's Convolution Conjecture on Gaussian Space.

[BibT_eX]

[DOI]

James R. Lee

Proceedings of the IEEE 56th Annual Symposium on Foundations of Computer Science, 2015

The entropic barrier: a simple and optimal universal self-concordant barrier.

[BibT_eX]

[DOI]

Proceedings of The 28th Conference on Learning Theory, 2015

2014

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

[BibT_eX]

[DOI]

CoRR, 2014

2011

A Polynomial Number of Random Points Does Not Determine the Volume of a Convex Body.

[BibT_eX]

[DOI]