Sashank Reddi
23 papers · 2015–2023 · 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 ↓+11 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (39) π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π€
Dynamic Duo
(16)
π§
Keyword Pioneer
π
Triple Crown
π¬
Deep Specialist
(14)
π
Renaissance Researcher
(5)
π₯
Unstoppable Β· Bronze
β
The Questioner
(4)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(105)
Venues
Top co-authors
Research topics
Machine Learning
(23)
Optimization & Theory Β· Machine Learning
(20)
Deep Learning
(11)
Architectures
(6)
Application Areas
(5)
Optimization & Theory Β· Deep Learning
(5)
Artificial Intelligence
(3)
Core Methods
(3)
Learning Types
(3)
Learning Paradigms
(2)
Techniques
(2)
Computer Science
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Security & Privacy
(1)
Keywords
federated learning
(4)
stochastic optimization
(3)
adaptive gradient method
(3)
knowledge distillation
(3)
non-convex optimization
(2)
representation learning
(2)
stochastic gradient descent
(2)
universal approximation
(2)
negative sampling
(2)
client drift
(2)
convergence analysis
(2)
information retrieval
(2)
attention mechanism
(2)
control variate
(2)
embedding dimension
(2)
natural language processing
(1)
bayesian inference
(1)
transformer architecture
(1)
graph laplacian
(1)
binary classification
(1)
Papers
What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models
NeurIPS 2023
In defense of dual-encoders for neural ranking
ICML 2022
Private Adaptive Optimization with Side information
ICML 2022
Robust Training of Neural Networks Using Scale Invariant Architectures
ICML 2022
A statistical perspective on distillation
ICML 2021
Breaking the centralized barrier for cross-device federated learning
NeurIPS 2021
Disentangling Sampling and Labeling Bias for Learning in Large-output Spaces
ICML 2021
Efficient Training of Retrieval Models using Negative Cache
NeurIPS 2021
Federated Composite Optimization
ICML 2021
RankDistil: Knowledge Distillation for Ranking
AISTATS 2021
Are Transformers universal approximators of sequence-to-sequence functions?
ICLR 2020
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
ICLR 2020
Learning to Learn by Zeroth-Order Oracle
ICLR 2020
Low-Rank Bottleneck in Multi-head Attention Models
ICML 2020
O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers
NeurIPS 2020
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
ICML 2020
Why are Adaptive Methods Good for Attention Models?
NeurIPS 2020
Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces
NeurIPS 2019
Escaping Saddle Points with Adaptive Gradient Methods
ICML 2019
Multilabel reductions: what is my loss optimising?
NeurIPS 2019
Adaptive Methods for Nonconvex Optimization
NeurIPS 2018
A Generic Approach for Escaping Saddle points
AISTATS 2018
On the High Dimensional Power of a Linear-Time Two Sample Test under Mean-shift Alternatives
AISTATS 2015