Viveck Cadambe

3 papers · 2016–2019 · 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 🌉 Interdisciplinary Bridge · Silver 🧭 Keyword Pioneer 📈 Trend Setter

Venues

NeurIPS (2) ICML (1)

Top co-authors

Mehrdad Mahdavi (2) Farzin Haddadpour (2) Mohammad Mahdi Kamani (2) Pulkit Grover (1) Sanghamitra Dutta (1)

Research topics

Deep Learning (3) Optimization & Theory · Deep Learning (3) Machine Learning (2) Mathematics & Optimization (2) Application Areas (2) Optimization (2) Optimization & Theory · Machine Learning (2) Computer Science (1) Systems (1)

Keywords

stochastic gradient descent (2) non-convex optimization (1) distributed optimization (1) distributed computing (1) communication efficiency (1) model averaging (1) straggler mitigation (1) distributed stochastic gradient descent (1) matrix multiplication (1) polyak-lojasiewicz condition (1) linear speedup (1) coded computation (1) data redundancy (1) communication round (1) linear transform (1) erasure code (1) periodic averaging (1) adaptive synchronization (1)

Papers

Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization NeurIPS 2019 Trading Redundancy for Communication: Speeding up Distributed SGD for Non-convex Optimization ICML 2019 Short-Dot: Computing Large Linear Transforms Distributedly Using Coded Short Dot Products NeurIPS 2016