Mahmut Kandemir

4 papers · 2020–2025 · 2 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 · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

ICLR (2) NeurIPS (2)

Top co-authors

Anand Sivasubramaniam (2) Morteza Ramezani (2) Mehrdad Mahdavi (2) Weilin Cong (2) Deeksha Chaudhary (1) Chita Das (1) Rui Zhang (1) Anup Sarma (1) Huaipan Jiang (1) Chita R. Das (1)

Research topics

Deep Learning (4) Machine Learning (3) Application Areas (3) Architectures (3) Artificial Intelligence (1) Natural Language Processing (1) Learning Paradigms (1) Techniques (1) Understanding (1)

Keywords

stochastic gradient descent (1) named entity recognition (1) convergence analysis (1) distributed learning (1) communication efficiency (1) model averaging (1) long short-term memory (1) recurrent neural network (1) deep neural network (1) sampling method (1) gpu acceleration (1) energy harvesting (1) adaptive training (1) graph convolutional network (1) language modelling (1) graph neural network (1) global correction (1) dropout rate (1) quantization level (1) intermittent power (1)

Papers

NExUME: Adaptive Training and Inference for DNNs under Intermittent Power Environments ICLR 2025 Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks ICLR 2022 Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training NeurIPS 2021 GCN meets GPU: Decoupling “When to Sample” from “How to Sample” NeurIPS 2020