Ali Ramezani-Kebrya

8 papers · 2020–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (14) 🏆 Grand Slam

Venues

ICLR (2) JMLR (2) NeurIPS (2) AAAI (1) ICML (1)

Top co-authors

Volkan Cevher (5) Kimon Antonakopoulos (3) Dan Alistarh (3) Ilia Markov (2) Daniel M. Roy (2) Fartash Faghri (2) Changkyu Choi (1) Zhengqing Wu (1) Zhiyuan Wu (1) Vitalii Aksenov (1)

Research topics

Machine Learning (8) Optimization & Theory · Machine Learning (6) Deep Learning (3) Application Areas (3) Artificial Intelligence (2) Core AI (2) Learning Types · Machine Learning (2) Architectures (1) Learning Types · Deep Learning (1) Optimization & Theory · Deep Learning (1)

Keywords

stochastic gradient descent (3) communication efficiency (3) distributed learning (3) gradient quantization (2) data-parallel training (2) label shift (1) maximum likelihood estimation (1) distributed training (1) optimization theory (1) adaptive learning rate (1) generalization bound (1) entropy regularization (1) generative adversarial network (1) momentum method (1) polyak-lojasiewicz condition (1) hate speech detection (1) wasserstein gan (1) neural network width (1) self-explaining model (1) rationale alignment (1)

Papers

Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection AAAI 2026 Addressing Label Shift in Distributed Learning via Entropy Regularization ICLR 2025 Layer-wise Quantization for Quantized Optimistic Dual Averaging ICML 2025 On the Generalization of Stochastic Gradient Descent with Momentum JMLR 2024 Distributed Extra-gradient with Optimal Complexity and Communication Guarantees ICLR 2023 NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization JMLR 2021 Subquadratic Overparameterization for Shallow Neural Networks NeurIPS 2021 Adaptive Gradient Quantization for Data-Parallel SGD NeurIPS 2020