Frederic Koehler

About Frederic Koehler

Frederic Koehler, With an exceptional h-index of 17 and a recent h-index of 16 (since 2020), a distinguished researcher at Massachusetts Institute of Technology, specializes in the field of Theoretical Computer Science, Machine Learning, High-Dimensional Statistics.

His recent articles reflect a diverse array of research interests and contributions to the field:

Optimistic rates: A unifying theory for interpolation learning and regularization in linear regression

Inferring Dynamic Networks from Marginals with Iterative Proportional Fitting

Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical Gaps

Uniform Convergence with Square-Root Lipschitz Loss

Feature adaptation for sparse linear regression

Universality of Spectral Independence with Applications to Fast Mixing in Spin Glasses

Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization

Influences in Mixing Measures

Frederic Koehler Information

University

Position

Graduate Student

Citations(all)

710

Citations(since 2020)

663

Cited By

175

hIndex(all)

17

hIndex(since 2020)

16

i10Index(all)

25

i10Index(since 2020)

25

Email

University Profile Page

Google Scholar

Frederic Koehler Skills & Research Interests

Theoretical Computer Science

Machine Learning

High-Dimensional Statistics

Top articles of Frederic Koehler

Optimistic rates: A unifying theory for interpolation learning and regularization in linear regression

ACM/JMS Journal of Data Science

2024/4/12

Frederic Koehler
Frederic Koehler

H-Index: 7

Nathan Srebro
Nathan Srebro

H-Index: 52

Inferring Dynamic Networks from Marginals with Iterative Proportional Fitting

arXiv preprint arXiv:2402.18697

2024/2/28

Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical Gaps

arXiv preprint arXiv:2402.15409

2024/2/23

Uniform Convergence with Square-Root Lipschitz Loss

Advances in Neural Information Processing Systems

2024/2/13

Zhen Dai
Zhen Dai

H-Index: 2

Frederic Koehler
Frederic Koehler

H-Index: 7

Feature adaptation for sparse linear regression

Advances in Neural Information Processing Systems

2024/2/13

Universality of Spectral Independence with Applications to Fast Mixing in Spin Glasses

2024

Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization

arXiv preprint arXiv:2310.01762

2023/10/3

Frederic Koehler
Frederic Koehler

H-Index: 7

Influences in Mixing Measures

arXiv preprint arXiv:2307.07625

2023/7/14

Sampling approximately low-rank Ising models: MCMC meets variational methods

2022/6/28

Entropic independence: optimal mixing of down-up random walks

2022/6/9

Kalman filtering with adversarial corruptions

2022/6/9

A spectral condition for spectral gap: fast mixing in high-temperature Ising models

Probability theory and related fields

2022/4

On the power of preconditioning in sparse linear regression

2022/2/7

Chow-liu++: Optimal prediction-centric learning of tree ising models

2022/2/7

Guy Bresler
Guy Bresler

H-Index: 16

Frederic Koehler
Frederic Koehler

H-Index: 7

Online and distribution-free robustness: Regression and contextual bandits with huber contamination

2022/2/7

Lower bounds on randomly preconditioned lasso via robust sparse designs

Advances in neural information processing systems

2022/12/6

A non-asymptotic moreau envelope theory for high-dimensional generalized linear models

Advances in Neural Information Processing Systems

2022/12/6

Frederic Koehler
Frederic Koehler

H-Index: 7

Pragya Sur
Pragya Sur

H-Index: 5

Reconstruction on trees and low-degree polynomials

Advances in Neural Information Processing Systems

2022/12/6

Frederic Koehler
Frederic Koehler

H-Index: 7

Elchanan Mossel
Elchanan Mossel

H-Index: 37

Statistical efficiency of score matching: The view from isoperimetry

arXiv preprint arXiv:2210.00726

2022/10/3

Frederic Koehler
Frederic Koehler

H-Index: 7

Andrej Risteski
Andrej Risteski

H-Index: 15

Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias

2021/12/13

See List of Professors in Frederic Koehler University(Massachusetts Institute of Technology)

Co-Authors

academic-engine