AR
Ali Ramezani-Kebrya
cs.LGstat.MLcs.AIcs.CLmath.OCcs.CRcs.CVcs.DCphysics.ao-ph
On Valency
published · living versionsW_q5a8g7q9·v1 · currentpublished
Intrinsic Information-Theoretic Analysis of ReLU Nets
with Johan Mylius-Kroken, Elisabeth Wetzer, Robert Jenssen, Kristoffer Knutsen Wickstrøm
1 version
Preprints & journals
15 papers in the corpus · 2018–2026Towards Self-Explainable Document Visual Question Answering with Chain-of-Explanation Predictions2605.06058v1 · Kjetil Indrehus, Adrian Duric, Changkyu Choi et al.2026 · 0 citationsarXiv
Beyond Accuracy: Decomposing the Reasoning Efficiency of LLMs2602.09805v2 · Daniel Kaiser, Arnoldo Frigessi, Ali Ramezani-Kebrya et al.2026 · 1 citationarXiv
Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection2511.07065v1 · Brage Eilertsen, R\oskva Bj\orgfinsd'ottir, Francielle Vargas et al.2025 · 2 citationsarXiv
Principled Operator Learning in Ocean Dynamics: The Role of Temporal Structure2510.09792v1 · Vahidreza Jahanmard, Ali Ramezani-Kebrya, Robinson Hordoir2025 · 0 citationsarXiv
CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density2509.18458v2 · Daniel Kaiser, Arnoldo Frigessi, Ali Ramezani-Kebrya et al.2025 · 0 citationsarXiv
Layer-wise Quantization for Quantized Optimistic Dual Averaging2505.14371v1 · Anh Duc Nguyen, Ilia Markov, Frank Zhengqing Wu et al.2025 · 0 citationsarXiv
Addressing Label Shift in Distributed Learning via Entropy Regularization2502.02544v1 · Zhiyuan Wu, Changkyu Choi, Xiangcheng Cao et al.2025 · 0 citationsarXiv
Distributed Extra-gradient with Optimal Complexity and Communication Guarantees2308.09187v1 · Ali Ramezani-Kebrya, Kimon Antonakopoulos, Igor Krawczuk et al.2023 · 0 citationsarXiv
Federated Learning under Covariate Shifts with Generalization Guarantees2306.05325v1 · Ali Ramezani-Kebrya, Fanghui Liu, Thomas Pethick et al.2023 · 3 citationsarXiv
MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks2207.07941v2 · Ali Ramezani-Kebrya, Iman Tabrizian, Fartash Faghri et al.2022 · 1 citationarXiv
Subquadratic Overparameterization for Shallow Neural Networks2111.01875v1 · Chaehwan Song, Ali Ramezani-Kebrya, Thomas Pethick et al.2021 · 5 citationsarXiv
On the Generalization of Stochastic Gradient Descent with Momentum2102.13653v2 · Ali Ramezani-Kebrya, Ashish Khisti, Ben Liang2021 · 9 citationsarXiv
Adaptive Gradient Quantization for Data-Parallel SGD2010.12460v1 · Fartash Faghri, Iman Tabrizian, Ilia Markov et al.2020 · 49 citationsarXiv
NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization1908.06077v2 · Ali Ramezani-Kebrya, Fartash Faghri, Ilya Markov et al.2019 · 13 citationsarXiv
On the Generalization of Stochastic Gradient Descent with Momentum1809.04564v3 · Ali Ramezani-Kebrya, Kimon Antonakopoulos, Volkan Cevher et al.2018 · 11 citationsarXiv
Career total: 34 works. 15 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.