Andrey Gromov

Publication Activity (10 Years)

Years Active: 2014-2024
Publications (10 Years): 13

Top Topics

Dice Similarity Coefficient

Highly Flexible

Top Venues

Nat. Mac. Intell.

Publications

Matthias Gerstgrasser, Rylan Schaeffer, Apratim Dey, Rafael Rafailov, Henry Sleight, John Hughes, Tomasz Korbak, Rajashree Agrawal, Dhruv Pai, Andrey Gromov, Daniel A. Roberts, Diyi Yang, David L. Donoho, Sanmi Koyejo
Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data. CoRR (2024)
Darshil Doshi, Aritra Das, Tianyu He, Andrey Gromov
To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets. ICLR (2024)
Darshil Doshi, Tianyu He, Aritra Das, Andrey Gromov
Grokking Modular Polynomials. CoRR (2024)
Rylan Schaeffer, Nika Zahedi, Mikail Khona, Dhruv Pai, Sang T. Truong, Yilun Du, Mitchell Ostrow, Sarthak Chandra, Andres Carranza, Ila Rani Fiete, Andrey Gromov, Sanmi Koyejo
Bridging Associative Memory and Probabilistic Modeling. CoRR (2024)
Tianyu He, Darshil Doshi, Aritra Das, Andrey Gromov
Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks. CoRR (2024)
Rylan Schaeffer, Victor Lecomte, Dhruv Bhandarkar Pai, Andres Carranza, Berivan Isik, Alyssa Unell, Mikail Khona, Thomas E. Yerxa, Yann LeCun, SueYeon Chung, Andrey Gromov, Ravid Shwartz-Ziv, Sanmi Koyejo
Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations. CoRR (2024)
Andrey Gromov, Kushal Tirumala, Hassan Shapourian, Paolo Glorioso, Daniel A. Roberts
The Unreasonable Ineffectiveness of the Deeper Layers. CoRR (2024)
Andrey Gromov
Grokking modular arithmetic. CoRR (2023)
Darshil Doshi, Tianyu He, Andrey Gromov
Critical Initialization of Wide and Deep Neural Networks using Partial Jacobians: General Theory and Applications. NeurIPS (2023)
Andrey Gromov
Deconstructing the generalization gap. Nat. Mac. Intell. 5 (12) (2023)
Darshil Doshi, Aritra Das, Tianyu He, Andrey Gromov
To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets. CoRR (2023)
Tianyu He, Darshil Doshi, Andrey Gromov
AutoInit: Automatic Initialization via Jacobian Tuning. CoRR (2022)
Darshil Doshi, Tianyu He, Andrey Gromov
Critical initialization of wide and deep neural networks through partial Jacobians: general theory and applications to LayerNorm. CoRR (2021)
Nikolay Borgest, Maksim Korovin, Andrey Gromov, Aleksey Gromov
The Concept of Automation in Conventional Systems Creation Applied to the Preliminary Aircraft Design. ACS (2014)