Dravyansh Sharma

According to our database, Dravyansh Sharma authored at least 33 papers between 2015 and 2025.

Collaborative distances:

• Dijkstra number of three.
• Erdős number of three.

2025

Distribution-dependent Generalization Bounds for Tuning Linear Regression Across Tasks.

Maria-Florina Balcan, Saumya Goyal, Dravyansh Sharma

CoRR, July, 2025

Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning.

Dravyansh Sharma, Alec Sun

CoRR, June, 2025

On Learning Verifiers for Chain-of-Thought Reasoning.

Maria-Florina Balcan, Avrim Blum, Zhiyuan Li, Dravyansh Sharma

CoRR, May, 2025

PAC Learning with Improvements.

Idan Attias, Avrim Blum, Keziah Naggita, Donya Saless, Dravyansh Sharma, Matthew R. Walter

CoRR, March, 2025

Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function.

Maria-Florina Balcan, Anh Tuan Nguyen, Dravyansh Sharma

CoRR, January, 2025

Algorithm Configuration for Structured Pfaffian Settings.

Maria-Florina Balcan, Anh Tuan Nguyen, Dravyansh Sharma

Trans. Mach. Learn. Res., 2025

Tuning Algorithmic and Architectural Hyperparameters in Graph-Based Semi-Supervised Learning with Provable Guarantees.

Ally Yalei Du, Eric Huang, Dravyansh Sharma

Proceedings of the Conference on Uncertainty in Artificial Intelligence, 2025

Learning Accurate and Interpretable Decision Trees (Extended Abstract).

Maria-Florina Balcan, Dravyansh Sharma

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025

Offline-to-Online Hyperparameter Transfer for Stochastic Bandits.

Dravyansh Sharma, Arun Sai Suggala

Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024

Provable Hyperparameter Tuning for Structured Pfaffian Settings.

Maria-Florina Balcan, Anh Tuan Nguyen, Dravyansh Sharma

CoRR, 2024

Subsidy design for better social outcomes.

Maria-Florina Balcan, Matteo Pozzi, Dravyansh Sharma

CoRR, 2024

Learning Accurate and Interpretable Decision Trees.

Maria-Florina Balcan, Dravyansh Sharma

Proceedings of the Uncertainty in Artificial Intelligence, 2024

Accelerating ERM for data-driven algorithm design using output-sensitive techniques.

Maria-Florina Balcan, Christopher Seiler, Dravyansh Sharma

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

No Internal Regret with Non-convex Loss Functions.

Dravyansh Sharma

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

An Analysis of Robustness of Non-Lipschitz Networks.

Maria-Florina Balcan, Avrim Blum, Dravyansh Sharma, Hongyang Zhang

J. Mach. Learn. Res., 2023

Reliable Learning for Test-time Attacks and Distribution Shift.

Maria-Florina Balcan, Steve Hanneke, Rattana Pukdee, Dravyansh Sharma

CoRR, 2023

Efficiently learning the graph for semi-supervised learning.

Dravyansh Sharma, Maxwell Jones

Proceedings of the Uncertainty in Artificial Intelligence, 2023

New Bounds for Hyperparameter Tuning of Regression Problems Across Instances.

Maria-Florina Balcan, Anh Nguyen, Dravyansh Sharma

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Reliable learning in challenging environments.

Maria-Florina Balcan, Steve Hanneke, Rattana Pukdee, Dravyansh Sharma

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Provably tuning the ElasticNet across instances.

Maria-Florina Balcan, Mikhail Khodak, Dravyansh Sharma, Ameet Talwalkar

CoRR, 2022

Faster algorithms for learning to link, align sequences, and price two-part tariffs.

Maria-Florina Balcan, Christopher Seiler, Dravyansh Sharma

CoRR, 2022

Provably tuning the ElasticNet across instances.

Maria-Florina Balcan, Misha Khodak, Dravyansh Sharma, Ameet Talwalkar

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Robustly-reliable learners under poisoning attacks.

Maria-Florina Balcan, Avrim Blum, Steve Hanneke, Dravyansh Sharma

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021

Data driven algorithms for limited labeled data learning.

Maria-Florina Balcan, Dravyansh Sharma

CoRR, 2021

Data driven semi-supervised learning.

Maria-Florina Balcan, Dravyansh Sharma

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Learning-to-learn non-convex piecewise-Lipschitz functions.

Maria-Florina Balcan, Mikhail Khodak, Dravyansh Sharma, Ameet Talwalkar

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

On the Power of Abstention and Data-Driven Decision Making for Adversarial Robustness.

Maria-Florina Balcan, Avrim Blum, Dravyansh Sharma, Hongyang Zhang

CoRR, 2020

Learning piecewise Lipschitz functions in changing environments.

Dravyansh Sharma, Maria-Florina Balcan, Travis Dick

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Online optimization of piecewise Lipschitz functions in changing environments.

Maria-Florina Balcan, Travis Dick, Dravyansh Sharma

CoRR, 2019

Better Morphology Prediction for Better Speech Systems.

Dravyansh Sharma, Melissa Wilson, Antoine Bruguier

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

2018

On Training and Evaluation of Grapheme-to-Phoneme Mappings with Limited Data.

Dravyansh Sharma

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

Dictionary Augmented Sequence-to-Sequence Neural Network for Grapheme to Phoneme Prediction.

Antoine Bruguier, Anton Bakhtin, Dravyansh Sharma

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

2015

On Greedy Maximization of Entropy.

Dravyansh Sharma, Ashish Kapoor, Amit Deshpande

Proceedings of the 32nd International Conference on Machine Learning, 2015