Pezeshki, Mohammad

18 publications

ICML 2025 Compositional Risk Minimization Divyat Mahajan, Mohammad Pezeshki, Charles Arnal, Ioannis Mitliagkas, Kartik Ahuja, Pascal Vincent

ICML 2025 Improving the Scaling Laws of Synthetic Data with Deliberate Practice Reyhane Askari-Hemmat, Mohammad Pezeshki, Elvis Dohmatob, Florian Bordes, Pietro Astolfi, Melissa Hall, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano

ICLR 2025 The Pitfalls of Memorization: When Memorization Hurts Generalization Reza Bayat, Mohammad Pezeshki, Elvis Dohmatob, David Lopez-Paz, Pascal Vincent

ICLRW 2025 Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification Konstantin Donhauser, Charles Arnal, Mohammad Pezeshki, Vivien Cabannes, David Lopez-Paz, Kartik Ahuja

NeurIPSW 2024 Compositional Risk Minimization Divyat Mahajan, Mohammad Pezeshki, Ioannis Mitliagkas, Kartik Ahuja, Pascal Vincent

NeurIPSW 2024 Deliberate Practice with Synthetic Data Reyhane Askari-Hemmat, Mohammad Pezeshki, Pietro Astolfi, Melissa Hall, Florian Bordes, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano

ICML 2024 Discovering Environments with XRM Mohammad Pezeshki, Diane Bouchacourt, Mark Ibrahim, Nicolas Ballas, Pascal Vincent, David Lopez-Paz

TMLR 2024 Feedback-Guided Data Synthesis for Imbalanced Classification Reyhane Askari Hemmat, Mohammad Pezeshki, Florian Bordes, Michal Drozdzal, Adriana Romero-Soriano

NeurIPSW 2024 The Pitfalls of Memorization: When Memorization Hinders Generalization Reza Bayat, Mohammad Pezeshki, Elvis Dohmatob, David Lopez-Paz, Pascal Vincent

NeurIPSW 2023 Discovering Environments with XRM Mohammad Pezeshki, Diane Bouchacourt, Mark Ibrahim, Nicolas Ballas, Pascal Vincent, David Lopez-Paz

NeurIPSW 2023 Feedback-Guided Data Synthesis for Imbalanced Classification Reyhane Askari Hemmat, Mohammad Pezeshki, Florian Bordes, Michal Drozdzal, Adriana Romero-Soriano

ICML 2022 Multi-Scale Feature Learning Dynamics: Insights for Double Descent Mohammad Pezeshki, Amartya Mitra, Yoshua Bengio, Guillaume Lajoie

CLeaR 2022 Simple Data Balancing Achieves Competitive Worst-Group-Accuracy Badr Youbi Idrissi, Martin Arjovsky, Mohammad Pezeshki, David Lopez-Paz

NeurIPS 2021 Gradient Starvation: A Learning Proclivity in Neural Networks Mohammad Pezeshki, Oumar Kaba, Yoshua Bengio, Aaron C. Courville, Doina Precup, Guillaume Lajoie

AISTATS 2019 Negative Momentum for Improved Game Dynamics Gauthier Gidel, Reyhane Askari Hemmat, Mohammad Pezeshki, Rémi Le Priol, Gabriel Huang, Simon Lacoste-Julien, Ioannis Mitliagkas

ICLR 2017 Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations David Krueger, Tegan Maharaj, János Kramár, Mohammad Pezeshki, Nicolas Ballas, Nan Rosemary Ke, Anirudh Goyal, Yoshua Bengio, Aaron C. Courville, Christopher J. Pal

ICML 2016 Deconstructing the Ladder Network Architecture Mohammad Pezeshki, Linxi Fan, Philemon Brakel, Aaron Courville, Yoshua Bengio

ICLR 2014 Deep Belief Networks for Image Denoising Mohammad Ali Keyvanrad, Mohammad Pezeshki, Mohammad Ali Homayounpour