Gilad Yehudai - RankMe

47 papers A* 17A 1B 1Journal 28

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Compositional Reasoning with Transformers, RNNs, and Chain of Thought. CoRR Gilad Yehudai, Noah Amsel, Joan Bruna
2025	J	`jnl`	Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers. CoRR Gilad Yehudai, Clayton Sanford, Maya Bechler-Speicher, Orr Fischer, Ran Gilad-Bachrach, Amir Globerson
2025	J	`jnl`	Emergence of Linear Truth Encodings in Language Models. CoRR Shauli Ravfogel, Gilad Yehudai, Tal Linzen, Joan Bruna, Alberto Bietti
2025	A	`conf`	Locally Optimal Descent for Dynamic Stepsize Scheduling. AISTATS Gilad Yehudai, Alon Cohen, Amit Daniely, Yoel Drori, Tomer Koren, Mariano Schain
2025	A*	`conf`	Logarithmic Width Suffices for Robust Memorization. COLT Amitsour Egosi, Gilad Yehudai, Ohad Shamir
2025	J	`jnl`	Logarithmic Width Suffices for Robust Memorization. CoRR Amitsour Egosi, Gilad Yehudai, Ohad Shamir
2025	J	`jnl`	Provable Unlearning with Gradient Ascent on Two-Layer ReLU Neural Networks. CoRR Odelia Melamed, Gilad Yehudai, Gal Vardi
2025	A*	`conf`	Quality over Quantity in Attention Layers: When Adding More Heads Hurts. ICLR Noah Amsel, Gilad Yehudai, Joan Bruna
2025	J	`jnl`	Querying Kernel Methods Suffices for Reconstructing their Training Data. CoRR Daniel Barzilai, Yuval Margalit, Eitan Gronich, Gilad Yehudai, Meirav Galun, Ronen Basri
2024	A*	`conf`	MALT Powers Up Adversarial Attacks. NeurIPS Odelia Melamed, Gilad Yehudai, Adi Shamir
2024	J	`jnl`	MALT Powers Up Adversarial Attacks. CoRR Odelia Melamed, Gilad Yehudai, Adi Shamir
2024	J	`jnl`	On the Benefits of Rank in Attention Layers. CoRR Noah Amsel, Gilad Yehudai, Joan Bruna
2024	J	`jnl`	On the Reconstruction of Training Data from Group Invariant Networks. CoRR Ran Elbaz, Gilad Yehudai, Meirav Galun, Haggai Maron
2024	J	`jnl`	Reconstructing Training Data From Real World Models Trained with Transfer Learning. CoRR Yakir Oz, Gilad Yehudai, Gal Vardi, Itai Antebi, Michal Irani, Niv Haim
2024	B	`conf`	RedEx: Beyond Fixed Representation Methods via Convex Optimization. ALT Amit Daniely, Mariano Schain, Gilad Yehudai
2024	J	`jnl`	RedEx: Beyond Fixed Representation Methods via Convex Optimization. CoRR Amit Daniely, Mariano Schain, Gilad Yehudai
2024	J	`jnl`	When Can Transformers Count to n? CoRR Gilad Yehudai, Haim Kaplan, Asma Ghandeharioun, Mor Geva, Amir Globerson
2023	J	`jnl`	Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Data Manifolds. CoRR Odelia Melamed, Gilad Yehudai, Gal Vardi
2023	A*	`conf`	Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces. NeurIPS Odelia Melamed, Gilad Yehudai, Gal Vardi
2023	A*	`conf`	Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses. NeurIPS Gon Buzaglo, Niv Haim, Gilad Yehudai, Gal Vardi, Yakir Oz, Yaniv Nikankin, Michal Irani
2023	J	`jnl`	Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses. CoRR Gon Buzaglo, Niv Haim, Gilad Yehudai, Gal Vardi, Yakir Oz, Yaniv Nikankin, Michal Irani
2023	A*	`conf`	From Tempered to Benign Overfitting in ReLU Neural Networks. NeurIPS Guy Kornowski, Gilad Yehudai, Ohad Shamir
2023	J	`jnl`	From Tempered to Benign Overfitting in ReLU Neural Networks. CoRR Guy Kornowski, Gilad Yehudai, Ohad Shamir
2023	J	`jnl`	Locally Optimal Descent for Dynamic Stepsize Scheduling. CoRR Gilad Yehudai, Alon Cohen, Amit Daniely, Yoel Drori, Tomer Koren, Mariano Schain
2023	J	`jnl`	Reconstructing Training Data from Multiclass Neural Networks. CoRR Gon Buzaglo, Niv Haim, Gilad Yehudai, Gal Vardi, Michal Irani
2022	A*	`conf`	Gradient Methods Provably Converge to Non-Robust Networks. NeurIPS Gal Vardi, Gilad Yehudai, Ohad Shamir
2022	J	`jnl`	Gradient Methods Provably Converge to Non-Robust Networks. CoRR Gal Vardi, Gilad Yehudai, Ohad Shamir
2022	A*	`conf`	On the Optimal Memorization Power of ReLU Neural Networks. ICLR Gal Vardi, Gilad Yehudai, Ohad Shamir
2022	A*	`conf`	Reconstructing Training Data From Trained Neural Networks. NeurIPS Niv Haim, Gal Vardi, Gilad Yehudai, Ohad Shamir, Michal Irani
2022	J	`jnl`	Reconstructing Training Data from Trained Neural Networks. CoRR Niv Haim, Gal Vardi, Gilad Yehudai, Ohad Shamir, Michal Irani
2022	A*	`conf`	Width is Less Important than Depth in ReLU Neural Networks. COLT Gal Vardi, Gilad Yehudai, Ohad Shamir
2022	J	`jnl`	Width is Less Important than Depth in ReLU Neural Networks. CoRR Gal Vardi, Gilad Yehudai, Ohad Shamir
2021	A*	`conf`	From Local Structures to Size Generalization in Graph Neural Networks. ICML Gilad Yehudai, Ethan Fetaya, Eli A. Meirom, Gal Chechik, Haggai Maron
2021	A*	`conf`	Learning a Single Neuron with Bias Using Gradient Descent. NeurIPS Gal Vardi, Gilad Yehudai, Ohad Shamir
2021	J	`jnl`	Learning a Single Neuron with Bias Using Gradient Descent. CoRR Gal Vardi, Gilad Yehudai, Ohad Shamir
2021	J	`jnl`	On the Optimal Memorization Power of ReLU Neural Networks. CoRR Gal Vardi, Gilad Yehudai, Ohad Shamir
2021	A*	`conf`	The Connection Between Approximation, Depth Separation and Learnability in Neural Networks. COLT Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir
2021	J	`jnl`	The Connection Between Approximation, Depth Separation and Learnability in Neural Networks. CoRR Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir
2021	A*	`conf`	The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks. COLT Itay Safran, Gilad Yehudai, Ohad Shamir
2020	A*	`conf`	Learning a Single Neuron with Gradient Methods. COLT Gilad Yehudai, Ohad Shamir
2020	J	`jnl`	Learning a Single Neuron with Gradient Methods. CoRR Gilad Yehudai, Ohad Shamir
2020	J	`jnl`	On Size Generalization in Graph Neural Networks. CoRR Gilad Yehudai, Ethan Fetaya, Eli A. Meirom, Gal Chechik, Haggai Maron
2020	A*	`conf`	Proving the Lottery Ticket Hypothesis: Pruning is All You Need. ICML Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir
2020	J	`jnl`	Proving the Lottery Ticket Hypothesis: Pruning is All You Need. CoRR Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir
2020	J	`jnl`	The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks. CoRR Itay Safran, Gilad Yehudai, Ohad Shamir
2019	A*	`conf`	On the Power and Limitations of Random Features for Understanding Neural Networks. NeurIPS Gilad Yehudai, Ohad Shamir
2019	J	`jnl`	On the Power and Limitations of Random Features for Understanding Neural Networks. CoRR Gilad Yehudai, Ohad Shamir