Sashank J. Reddi
20 papers · 2010–2025 · 4 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 ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (44) 🏃 Academic Marathon · Full 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🤝
Dynamic Duo
(12)
🔬
Deep Specialist
(10)
🚀
Conference Pioneer
❓
The Questioner
(2)
💎
Century Club · Bronze
🗃️
Keyword Collector
(104)
Venues
Top co-authors
Research topics
Machine Learning
(19)
Optimization & Theory · Machine Learning
(17)
Deep Learning
(9)
Mathematics & Optimization
(6)
Optimization
(6)
Optimization & Theory · Deep Learning
(6)
Artificial Intelligence
(5)
Core Methods
(5)
Architectures
(4)
Learning Types · Deep Learning
(4)
Learning Paradigms
(3)
Core AI
(2)
Learning Types · Machine Learning
(2)
Natural Language Processing
(1)
Application Areas
(1)
Keywords
variance reduction
(5)
stochastic optimization
(5)
stochastic gradient descent
(3)
non-convex optimization
(3)
neural network optimization
(3)
adaptive optimization
(3)
convergence analysis
(2)
transfer learning
(2)
language model
(2)
stationary point
(2)
reasoning ability
(2)
convergence rate
(2)
gradient descent
(2)
preconditioners
(2)
bayesian inference
(1)
convex optimization
(1)
stochastic gradient
(1)
transformer architecture
(1)
federated learning
(1)
finite-sum optimization
(1)
Papers
Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
ICML 2025
Efficient stagewise pretraining via progressive subnetworks
ICLR 2025
Reasoning with Latent Thoughts: On the Power of Looped Transformers
ICLR 2025
Structured Preconditioners in Adaptive Optimization: A Unified Analysis
ICML 2025
Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?
ICML 2024
On the Inductive Bias of Stacking Towards Improving Reasoning
NeurIPS 2024
Simplicity Bias via Global Convergence of Sharpness Minimization
ICML 2024
Differentially Private Adaptive Optimization with Delayed Preconditioners
ICLR 2023
Efficient Training of Language Models using Few-Shot Learning
ICML 2023
The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers
ICLR 2023
Adaptive Federated Optimization
ICLR 2021
Can gradient clipping mitigate label noise?
ICLR 2020
Stochastic Negative Mining for Learning with Large Output Spaces
AISTATS 2019
On the Convergence of Adam and Beyond
ICLR 2018
Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization
NeurIPS 2016
Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds
NeurIPS 2016
Stochastic Variance Reduction for Nonconvex Optimization
ICML 2016
Variance Reduction in Stochastic Gradient Langevin Dynamics
NeurIPS 2016
On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants
NeurIPS 2015
MAP estimation in Binary MRFs via Bipartite Multi-cuts
NeurIPS 2010