Hossein Mobahi

64 papers A* 19A 1B 2C 1Journal 30Unranked 9

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Data-Aware Random Feature Kernel for Transformers. CoRR Amirhossein Farzam, Hossein Mobahi, Nolan Andrew Miller, Luke Sernau
2025	A*	`conf`	Avoiding spurious sharpness minimization broadens applicability of SAM. ICML Sidak Pal Singh, Hossein Mobahi, Atish Agarwala, Yann N. Dauphin
2025	J	`jnl`	Avoiding spurious sharpness minimization broadens applicability of SAM. CoRR Sidak Pal Singh, Hossein Mobahi, Atish Agarwala, Yann N. Dauphin
2025	A*	`conf`	PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving. EMNLP Mihir Parmar, Xin Liu, Palash Goyal, Yanfei Chen, Long T. Le, Swaroop Mishra, Hossein Mobahi, Jindong Gu, Zifeng Wang, Hootan Nakhost, Chitta Baral, Chen-Yu Lee, Tomas Pfister, Hamid Palangi
2025	J	`jnl`	PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving. CoRR Mihir Parmar, Xin Liu, Palash Goyal, Yanfei Chen, Long T. Le, Swaroop Mishra, Hossein Mobahi, Jindong Gu, Zifeng Wang, Hootan Nakhost, Chitta Baral, Chen-Yu Lee, Tomas Pfister, Hamid Palangi
2024	J	`jnl`	Neglected Hessian component explains mysteries in Sharpness regularization. CoRR Yann N. Dauphin, Atish Agarwala, Hossein Mobahi
2024	A*	`conf`	Neglected Hessian component explains mysteries in sharpness regularization. NeurIPS Yann N. Dauphin, Atish Agarwala, Hossein Mobahi
2024	A*	`conf`	On the Foundations of Shortcut Learning. ICLR Katherine L. Hermann, Hossein Mobahi, Thomas Fel, Michael Curtis Mozer
2023	A*	`conf`	On student-teacher deviations in distillation: does it pay to disobey? NeurIPS Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar
2023	J	`jnl`	On student-teacher deviations in distillation: does it pay to disobey? CoRR Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar
2023	J	`jnl`	On the Foundations of Shortcut Learning. CoRR Katherine L. Hermann, Hossein Mobahi, Thomas Fel, Michael C. Mozer
2023	A*	`conf`	Sharpness-Aware Minimization Leads to Low-Rank Features. NeurIPS Maksym Andriushchenko, Dara Bahri, Hossein Mobahi, Nicolas Flammarion
2023	J	`jnl`	Sharpness-Aware Minimization Leads to Low-Rank Features. CoRR Maksym Andriushchenko, Dara Bahri, Hossein Mobahi, Nicolas Flammarion
2023	J	`jnl`	The Low-Rank Simplicity Bias in Deep Networks. Trans. Mach. Learn. Res. Minyoung Huh, Hossein Mobahi, Richard Zhang, Brian Cheung, Pulkit Agrawal, Phillip Isola
2022	—	`conf`	Sharpness-Aware Minimization Improves Language Model Generalization. ACL (1) Dara Bahri, Hossein Mobahi, Yi Tay
2021	A*	`conf`	A unifying view on implicit bias in training linear neural networks. ICLR Chulhee Yun, Shankar Krishnan, Hossein Mobahi
2021	J	`jnl`	Sharpness-Aware Minimization Improves Language Model Generalization. CoRR Dara Bahri, Hossein Mobahi, Yi Tay
2021	A*	`conf`	Sharpness-aware Minimization for Efficiently Improving Generalization. ICLR Pierre Foret, Ariel Kleiner, Hossein Mobahi, Behnam Neyshabur
2021	J	`jnl`	The Low-Rank Simplicity Bias in Deep Networks. CoRR Minyoung Huh, Hossein Mobahi, Richard Zhang, Brian Cheung, Pulkit Agrawal, Phillip Isola
2020	J	`jnl`	A Unifying View on Implicit Bias in Training Linear Neural Networks. CoRR Chulhee Yun, Shankar Krishnan, Hossein Mobahi
2020	J	`jnl`	Data Augmentation via Structured Adversarial Perturbations. CoRR Calvin Luo, Hossein Mobahi, Samy Bengio
2020	A*	`conf`	Fantastic Generalization Measures and Where to Find Them. ICLR Yiding Jiang, Behnam Neyshabur, Hossein Mobahi, Dilip Krishnan, Samy Bengio
2020	—	`conf`	Methods and Analysis of The First Competition in Predicting Generalization of Deep Learning. NeurIPS (Competition and Demos) Yiding Jiang, Parth Natekar, Manik Sharma, Sumukh K. Aithal, Dhruva Kashyap, Natarajan Subramanyam, Carlos Lassance, Daniel M. Roy, Gintare Karolina Dziugaite, Suriya Gunasekar, Isabelle Guyon, Pierre Foret, Scott Yak, Hossein Mobahi, Behnam Neyshabur, Samy Bengio
2020	J	`jnl`	NeurIPS 2020 Competition: Predicting Generalization in Deep Learning. CoRR Yiding Jiang, Pierre Foret, Scott Yak, Daniel M. Roy, Hossein Mobahi, Gintare Karolina Dziugaite, Samy Bengio, Suriya Gunasekar, Isabelle Guyon, Behnam Neyshabur
2020	A*	`conf`	Self-Distillation Amplifies Regularization in Hilbert Space. NeurIPS Hossein Mobahi, Mehrdad Farajtabar, Peter L. Bartlett
2020	J	`jnl`	Self-Distillation Amplifies Regularization in Hilbert Space. CoRR Hossein Mobahi, Mehrdad Farajtabar, Peter L. Bartlett
2020	J	`jnl`	Sharpness-Aware Minimization for Efficiently Improving Generalization. CoRR Pierre Foret, Ariel Kleiner, Hossein Mobahi, Behnam Neyshabur
2019	J	`jnl`	A Closed-Form Learned Pooling for Deep Classification Networks. CoRR Vighnesh Birodkar, Hossein Mobahi, Dilip Krishnan, Samy Bengio
2019	J	`jnl`	Fantastic Generalization Measures and Where to Find Them. CoRR Yiding Jiang, Behnam Neyshabur, Hossein Mobahi, Dilip Krishnan, Samy Bengio
2019	—	`conf`	Predicting the Generalization Gap in Deep Networks with Margin Distributions. ICLR (Poster) Yiding Jiang, Dilip Krishnan, Hossein Mobahi, Samy Bengio
2019	J	`jnl`	Semantic Redundancies in Image-Classification Datasets: The 10% You Don't Need. CoRR Vighnesh Birodkar, Hossein Mobahi, Samy Bengio
2018	A*	`conf`	Large Margin Deep Networks for Classification. NeurIPS Gamaleldin F. Elsayed, Dilip Krishnan, Hossein Mobahi, Kevin Regan, Samy Bengio
2018	J	`jnl`	Large Margin Deep Networks for Classification. CoRR Gamaleldin F. Elsayed, Dilip Krishnan, Hossein Mobahi, Kevin Regan, Samy Bengio
2018	J	`jnl`	Predicting the Generalization Gap in Deep Networks with Margin Distributions. CoRR Yiding Jiang, Dilip Krishnan, Hossein Mobahi, Samy Bengio
2017	A*	`conf`	Homotopy Analysis for Tensor PCA. COLT Anima Anandkumar, Yuan Deng, Rong Ge, Hossein Mobahi
2016	J	`jnl`	A Theory of Local Matching: SIFT and Beyond. CoRR Hossein Mobahi, Stefano Soatto
2016	J	`jnl`	Homotopy Method for Tensor Principal Component Analysis. CoRR Anima Anandkumar, Yuan Deng, Rong Ge, Hossein Mobahi
2016	J	`jnl`	Training Recurrent Neural Networks by Diffusion. CoRR Hossein Mobahi
2015	A*	`conf`	A Theoretical Analysis of Optimization by Gaussian Continuation. AAAI Hossein Mobahi, John W. Fisher III
2015	—	`conf`	Learning with a Wasserstein Loss. NIPS Charlie Frogner, Chiyuan Zhang, Hossein Mobahi, Mauricio Araya-Polo, Tomaso A. Poggio
2015	J	`jnl`	Learning with a Wasserstein Loss. CoRR Charlie Frogner, Chiyuan Zhang, Hossein Mobahi, Mauricio Araya-Polo, Tomaso A. Poggio
2015	A*	`conf`	The aperture problem for refractive motion. CVPR Tianfan Xue, Hossein Mobahi, Frédo Durand, William T. Freeman
2014	A*	`conf`	A Compositional Model for Low-Dimensional Image Set Representation. CVPR Hossein Mobahi, Ce Liu, William T. Freeman
2014	—	`conf`	Coarse-to-Fine Minimization of Some Common Nonconvexities. EMMCVPR Hossein Mobahi, John W. Fisher III
2014	—	`conf`	On the Link between Gaussian Homotopy Continuation and Convex Envelopes. EMMCVPR Hossein Mobahi, John W. Fisher III
2012	—	`ch.`	Deep Learning via Semi-supervised Embedding. Neural Networks: Tricks of the Trade (2nd ed.) Jason Weston, Frédéric Ratle, Hossein Mobahi, Ronan Collobert
2012	—	`—`	Optimization by Gaussian smoothing with application to geometric alignment Hossein Mobahi
2012	A*	`conf`	Seeing through the blur. CVPR Hossein Mobahi, C. Lawrence Zitnick, Yi Ma
2012	J	`jnl`	Toward a Practical Face Recognition System: Robust Alignment and Illumination by Sparse Representation. IEEE Trans. Pattern Anal. Mach. Intell. Andrew Wagner, John Wright, Arvind Ganesh, Zihan Zhou, Hossein Mobahi, Yi Ma
2011	—	`conf`	Holistic 3D reconstruction of urban structures from low-rank textures. ICCV Workshops Hossein Mobahi, Zihan Zhou, Allen Y. Yang, Yi Ma
2011	J	`jnl`	Segmentation of Natural Images by Texture and Boundary Compression. Int. J. Comput. Vis. Hossein Mobahi, Shankar R. Rao, Allen Y. Yang, Shankar S. Sastry, Yi Ma
2010	J	`jnl`	Segmentation of Natural Images by Texture and Boundary Compression CoRR Hossein Mobahi, Shankar R. Rao, Allen Y. Yang, S. Shankar Sastry, Yi Ma
2009	C	`conf`	Data-driven image completion by image patch subspaces. PCS Hossein Mobahi, Shankar R. Rao, Yi Ma
2009	A*	`conf`	Deep learning from temporal coherence in video. ICML Hossein Mobahi, Ronan Collobert, Jason Weston
2009	A*	`conf`	Face recognition with contiguous occlusion using markov random fields. ICCV Zihan Zhou, Andrew Wagner, Hossein Mobahi, John Wright, Yi Ma
2009	—	`conf`	Learning Topology of Curves with Application to Clustering. AAAI Fall Symposium: Manifold Learning and Its Applications Hossein Mobahi, Shankar R. Rao, Yi Ma
2009	—	`conf`	Natural Image Segmentation with Adaptive Texture and Boundary Encoding. ACCV (1) Shankar R. Rao, Hossein Mobahi, Allen Y. Yang, Shankar Sastry, Yi Ma
2007	J	`jnl`	A Biologically Inspired Method for Conceptual Imitation Using Reinforcement Learning. Appl. Artif. Intell. Hossein Mobahi, Majid Nili Ahmadabadi, Babak Nadjar Araabi
2006	J	`jnl`	Swarm contours: A fast self-organization approach for snake initialization. Complex. Hossein Mobahi, Majid Nili Ahmadabadi, Babak Nadjar Araabi
2005	A*	`conf`	Concept Oriented Imitation Towards Verbal Human-Robot Interaction. ICRA Hossein Mobahi, Majid Nili Ahmadabadi, Babak Nadjar Araabi
2005	J	`jnl`	HCI Applications for aiding children with mental disorders. ACM Crossroads Hossein Mobahi, Karrie G. Karahalios
2004	A	`conf`	Fast initialization of active contours. IROS Hossein Mobahi, Majid Nili Ahmadabadi, Babak Nadjar Araabi
2004	B	`conf`	Peak stick RBF network for online system identification. IJCNN Hossein Mobahi, Farrokh Janabi-Sharifi
2003	B	`conf`	Fuzzy perception, emotion and expression for interactive robots. SMC Hossein Mobahi, Shahin Ansari