Marton Havasi

According to our database, Marton Havasi authored at least 13 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Understanding and Mitigating Tokenization Bias in Language Models.

Buu Phan, Marton Havasi, Matthew J. Muckley, Karen Ullrich

CoRR, 2024

Guarantee Regions for Local Explanations.

Marton Havasi, Sonali Parbhoo, Finale Doshi-Velez

CoRR, 2024

2022

Does the explanation satisfy your needs?: A unified view of properties of explanations.

Zixi Chen, Varshini Subhash, Marton Havasi, Weiwei Pan, Finale Doshi-Velez

CoRR, 2022

Addressing Leakage in Concept Bottleneck Models.

Marton Havasi, Sonali Parbhoo, Finale Doshi-Velez

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

Learning Optimal Summaries of Clinical Time-series with Concept Bottleneck Models.

Carissa Wu, Sonali Parbhoo, Marton Havasi, Finale Doshi-Velez

Proceedings of the Machine Learning for Healthcare Conference, 2022

2021

Sampling the Variational Posterior with Local Refinement.

Marton Havasi, Jasper Snoek, Dustin Tran, Jonathan Gordon, José Miguel Hernández-Lobato

Entropy, 2021

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning.

Zachary Nado, Neil Band, Mark Collier, Josip Djolonga, Michael W. Dusenberry, Sebastian Farquhar, Angelos Filos, Marton Havasi, Rodolphe Jenatton, Ghassen Jerfel, Jeremiah Z. Liu, Zelda Mariet, Jeremy Nixon, Shreyas Padhy, Jie Ren, Tim G. J. Rudner, Yeming Wen, Florian Wenzel, Kevin Murphy, D. Sculley, Balaji Lakshminarayanan, Jasper Snoek, Yarin Gal, Dustin Tran

CoRR, 2021

Training independent subnetworks for robust prediction.

Marton Havasi, Rodolphe Jenatton, Stanislav Fort, Jeremiah Zhe Liu, Jasper Snoek, Balaji Lakshminarayanan, Andrew Mingbo Dai, Dustin Tran

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding.

Gergely Flamich, Marton Havasi, José Miguel Hernández-Lobato

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

A comprehensive methodology to determine optimal coherence interfaces for many-accelerator SoCs.

Kshitij Bhardwaj, Marton Havasi, Yuan Yao, David M. Brooks, José Miguel Hernández-Lobato, Gu-Yeon Wei

Proceedings of the ISLPED '20: ACM/IEEE International Symposium on Low Power Electronics and Design, 2020

2019

Determining Optimal Coherency Interface for Many-Accelerator SoCs Using Bayesian Optimization.

Kshitij Bhardwaj, Marton Havasi, Yuan Yao, David M. Brooks, José Miguel Hernández-Lobato, Gu-Yeon Wei

IEEE Comput. Archit. Lett., 2019

Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters.

Marton Havasi, Robert Peharz, José Miguel Hernández-Lobato

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo.

Marton Havasi, José Miguel Hernández-Lobato, Juan José Murillo-Fuentes

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018