Author of the publication

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time.

M. Wortsman, G. Ilharco, S. Gadre, R. Roelofs, R. Lopes, A. Morcos, H. Namkoong, A. Farhadi, Y. Carmon, S. Kornblith, and L. Schmidt. ICML, volume 162 of Proceedings of Machine Learning Research, page 23965-23998. PMLR, (2022)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

Yair Schiftan

Other publications of authors with the same name

Comparison of the Achievable Rates in OFDM and Single Carrier Modulation with I.I.D. Inputs.Y. Carmon, S. Shamai, and T. Weissman. CoRR, (2013)First-Order Methods for Nonconvex Quadratic Minimization.Y. Carmon, and J. Duchi. SIAM Rev., 62 (2): 395-436 (2020)A Whole New Ball Game: A Primal Accelerated Method for Matrix Games and Minimizing the Maximum of Smooth Functions.Y. Carmon, A. Jambulapati, Y. Jin, and A. Sidford. CoRR, (2023)Acceleration with a Ball Optimization Oracle.Y. Carmon, A. Jambulapati, Q. Jiang, Y. Jin, Y. Lee, A. Sidford, and K. Tian. NeurIPS, (2020)Analysis of Krylov Subspace Solutions of Regularized Non-Convex Quadratic Problems.Y. Carmon, and J. Duchi. NeurIPS, page 10728-10738. (2018)Variance Reduction for Matrix Games.Y. Carmon, Y. Jin, A. Sidford, and K. Tian. NeurIPS, page 11377-11388. (2019)Eventually-stationary policies for Markov decision models with non-constant discounting.Y. Carmon, and A. Shwartz. VALUETOOLS, page 63. ICST/ACM, (2008)A Rank-1 Sketch for Matrix Multiplicative Weights.Y. Carmon, J. Duchi, A. Sidford, and K. Tian. COLT, volume 99 of Proceedings of Machine Learning Research, page 589-623. PMLR, (2019)Optimal and Adaptive Monteiro-Svaiter Acceleration.Y. Carmon, D. Hausler, A. Jambulapati, Y. Jin, and A. Sidford. NeurIPS, (2022)Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond.I. Kreisler, M. Nacson, D. Soudry, and Y. Carmon. ICML, volume 202 of Proceedings of Machine Learning Research, page 17684-17744. PMLR, (2023)

BibSonomy

Disambiguation of "Carmon, Yair"

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time.

Please choose a person to relate this publication to

Yair Schiftan

Other publications of authors with the same name

Disambiguation

BibSonomy

Disambiguation of "Carmon, Yair"

copydeleteadd this publication to your clipboardcommunity posthistory of this postURLDOIBibTeXEndNoteAPAChicagoDIN 1505HarvardMSOffice XML Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time.

Please choose a person to relate this publication to

Yair Schiftan

Other publications of authors with the same name

Disambiguation

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time.