NewEvery arXiv paper, its researchers & institutions — mapped.
papers

Publications (28)

cs.LG2024

Learning Neural Networks with Sparse Activations

Pranjal Awasthi, Nishanth Dikkala, Pritish Kamath +1

cs.LG2017

Testing Symmetric Markov Chains from a Single Trajectory

Constantinos Daskalakis, Nishanth Dikkala, Nick Gravin

cs.CV2024

ReMI: A Dataset for Reasoning with Multiple Images

Mehran Kazemi, Nishanth Dikkala, Ankit Anand +8

cs.LG2021

For Manifold Learning, Deep Neural Networks can be Locality Sensitive Hash Functions

Nishanth Dikkala, Gal Kaplun, Rina Panigrahy

cs.LG2025

StagFormer: Time Staggering Transformer Decoding for RunningLayers In Parallel

Dylan Cutler, Arun Kandoor, Nishanth Dikkala +3

cs.CL2025

Reasoning with Latent Thoughts: On the Power of Looped Transformers

Nikunj Saunshi, Nishanth Dikkala, Zhiyuan Li +2

math.PR2017

Concentration of Multilinear Functions of the Ising Model with Applications to Network Data

Constantinos Daskalakis, Nishanth Dikkala, Gautam Kamath

econ.EM2020

Minimax Estimation of Conditional Moment Models

Nishanth Dikkala, Greg Lewis, Lester Mackey +1

cs.LG2024

Causal Language Modeling Can Elicit Search and Reasoning Capabilities on Logic Puzzles

Kulin Shah, Nishanth Dikkala, Xin Wang +1

math.ST2020

Learning Ising models from one or multiple samples

Yuval Dagan, Constantinos Daskalakis, Nishanth Dikkala +1

cs.LG2022

A Theoretical View on Sparsely Activated Networks

Cenk Baykal, Nishanth Dikkala, Rina Panigrahy +2

stat.ML2020

Logistic-Regression with peer-group effects via inference in higher order Ising models

Constantinos Daskalakis, Nishanth Dikkala, Ioannis Panageas

cs.LG2018

HOGWILD!-Gibbs can be PanAccurate

Constantinos Daskalakis, Nishanth Dikkala, Siddhartha Jayanti

cs.LG2023

Alternating Updates for Efficient Transformers

Cenk Baykal, Dylan Cutler, Nishanth Dikkala +3

cs.LG2022

Do More Negative Samples Necessarily Hurt in Contrastive Learning?

Pranjal Awasthi, Nishanth Dikkala, Pritish Kamath

cs.LG2019

Learning from weakly dependent data under Dobrushin's condition

Yuval Dagan, Constantinos Daskalakis, Nishanth Dikkala +1

cs.CL2025

BIG-Bench Extra Hard

Mehran Kazemi, Bahare Fatemi, Hritik Bansal +17

cs.DS2019

Testing Ising Models

Constantinos Daskalakis, Nishanth Dikkala, Gautam Kamath

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

cs.LG2019

Regression from Dependent Observations

Constantinos Daskalakis, Nishanth Dikkala, Ioannis Panageas

cs.LG2019

From Soft Classifiers to Hard Decisions: How fair can we be?

Ran Canetti, Aloni Cohen, Nishanth Dikkala +3

cs.CL2024

Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries

Kiran Vodrahalli, Santiago Ontanon, Nilesh Tripuraneni +21

cs.DS2016

Tight Hardness Results for Maximum Weight Rectangles

Arturs Backurs, Nishanth Dikkala, Christos Tzamos

cs.LG2025

A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning

Guan Zhe Hong, Nishanth Dikkala, Enming Luo +3

cs.GT2015

Effect of Strategic Grading and Early Offers in Matching Markets

Hedyeh Beyhaghi, Nishanth Dikkala, Eva Tardos

cs.CL2026

Gemma 4 Technical Report

Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320

cs.LG2023

The Power of External Memory in Increasing Predictive Model Capacity

Cenk Baykal, Dylan J Cutler, Nishanth Dikkala +3

cs.LG2021

Statistical Estimation from Dependent Data

Yuval Dagan, Constantinos Daskalakis, Nishanth Dikkala +2