Sashank J. Reddi

Computer Science · Physical Sciences

30h-index4.7kcitations93works0.42yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Stochastic Gradient Optimization Techniques(39), Sparse and Compressive Sensing Techniques(21), Privacy-Preserving Technologies in Data(15), Domain Adaptation and Few-Shot Learning(11), Statistical Methods and Inference(9)

Publications93 total

Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
arXiv (Cornell University)·2025Open Access
Structured Preconditioners in Adaptive Optimization: A Unified Analysis
arXiv (Cornell University)·2025Open Access
Reasoning with Latent Thoughts: On the Power of Looped Transformers
arXiv (Cornell University)·2025Open Access
On the Role of Depth and Looping for In-Context Learning with Task Diversity
arXiv (Cornell University)·2024Open Access
A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs
arXiv (Cornell University)·2024· 1 citedOpen Access
Simplicity Bias via Global Convergence of Sharpness Minimization
arXiv (Cornell University)·2024Open Access
Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?
arXiv (Cornell University)·2024Open Access
On the Inductive Bias of Stacking Towards Improving Reasoning
arXiv (Cornell University)·2024· 1 citedOpen Access
Efficient Document Ranking with Learnable Late Interactions
arXiv (Cornell University)·2024· 3 citedOpen Access
Landscape-Aware Growing: The Power of a Little LAG
arXiv (Cornell University)·2024Open Access
Efficient Stagewise Pretraining via Progressive Subnetworks
arXiv (Cornell University)·2024Open Access
On the Inductive Bias of Stacking Towards Improving Reasoning
2024
The Inductive Bias of Flatness Regularization for Deep Matrix Factorization
arXiv (Cornell University)·2023Open Access
Depth Dependence of $μ$P Learning Rates in ReLU MLPs
arXiv (Cornell University)·2023Open Access
Differentially Private Adaptive Optimization with Delayed Preconditioners
arXiv (Cornell University)·2022· 3 citedOpen Access
On the Algorithmic Stability and Generalization of Adaptive Optimization Methods
arXiv (Cornell University)·2022Open Access
The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers
arXiv (Cornell University)·2022· 10 citedOpen Access
Private Adaptive Optimization with Side Information
arXiv (Cornell University)·2022· 3 citedOpen Access
Robust Training of Neural Networks Using Scale Invariant Architectures
arXiv (Cornell University)·2022· 1 citedOpen Access
FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clients
arXiv (Cornell University)·2022· 8 citedOpen Access
page 1 of 5Next →

Frequent Co-authors

Barnabás Póczos(19), Sanjiv Kumar(18), Suvrit Sra(17), Satyen Kale(10), Ankit Singh Rawat(9), Alex Smola(7), Sai Praneeth Karimireddy(7), Srinadh Bhojanapalli(7), Alexander J. Smola(7), Ananda Theertha Suresh(5), Chulhee Yun(5), Ahmed Hefny(4), Mehryar Mohri(4), Sebastian U. Stich(4), Aaditya Ramdas(4), Aarti Singh(4), Larry Wasserman(4), Manzil Zaheer(3), Sanjiv Kumar(3), Martin Jaggi(3)