Enric Boix-Adsera
I am a final-year PhD student in the EECS department at MIT, advised by Guy Bresler and Philippe Rigollet. I received my undergraduate degree in mathematics from Princeton University, where I was advised by Emmanuel Abbe. I am grateful to be generously supported by an NSF Graduate Research Fellowship, a Siebel Fellowship, and an Apple AI/ML fellowship.
My research focuses on building a mathematical science of deep learning. I aim to characterize the fundamental mechanisms driving how neural networks learn, so as to push forward the state-of-the-art practice in deep learning and enable us to create more efficient and more trustworthy systems.
Publications [sorted by year | sorted by topic]
Publications [sorted by year | sorted by topic]
* denotes equally-contributing first authors and (αβ) denotes alphabetical order
2024
2023
-
When can transformers reason with abstract symbols?
EB*, Omid Saremi, Emmanuel Abbe, Samy Bengio, Etai Littwin, Joshua Susskind.
International Conference on Learning Representations (ICLR'24).
-
Prompt design as an inverse problem
Rimon Melamed, Lucas H. McCabe, Tanay Wakhare, Yejin Kim, H. Howie Huang, EB.
Preprint.
-
Transformers learn through gradual rank increase
EB*, Etai Littwin*, Emmanuel Abbe, Samy Bengio, Joshua Susskind.
Conference on Neural Information Processing Systems (NeurIPS'23).
-
Tight conditions for when the NTK approximation is valid
(αβ) EB, Etai Littwin.
Transactions on Machine Learning Research (TMLR).
-
SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics
(αβ) Emmanuel Abbe, EB, Theodor Misiakiewicz.
Conference on Learning Theory (COLT'23).
2022
2021
2020
2019
-
The Average-Case Complexity of Counting Cliques in Erdos-Renyi Hypergraphs
(αβ) EB, Matthew Brennan, Guy Bresler.
Foundations of Computer Science (FOCS'19).
Invited to the SIAM Journal on Computing Special Issue for FOCS 2019
-
Sample-Efficient Active Learning of Causal Trees
Kristjan Greenewald*, Dmitriy Katz-Rogozhnikov*, Karthikeyan Shanmugam*, Sara Magliacane, Murat Kocaoglu, EB, Guy Bresler.
Conference on Neural Information Processing Systems (NeurIPS'19).
-
Subadditivity Beyond Trees and the Chi-Squared Mutual Information
(αβ) Emmanuel Abbe, EB.
IEEE International Symposium on Information Theory (ISIT'19).
-
Randomized Concurrent Set Union and Generalized Wake-Up
Siddhartha Jayanti*, Robert E. Tarjan*, EB.
Symposium on Principles of Distributed Computing (PODC'19).
2018
* denotes equally-contributing first authors and (αβ) denotes alphabetical order
Learning
-
Towards a theory of model distillation
EB.
Preprint.
-
When can transformers reason with abstract symbols?
EB*, Omid Saremi, Emmanuel Abbe, Samy Bengio, Etai Littwin, Joshua Susskind.
International Conference on Learning Representations (ICLR'24).
-
Prompt design as an inverse problem
Rimon Melamed, Lucas H. McCabe, Tanay Wakhare, Yejin Kim, H. Howie Huang, EB.
Preprint.
-
Transformers learn through gradual rank increase
EB*, Etai Littwin*, Emmanuel Abbe, Samy Bengio, Joshua Susskind.
Conference on Neural Information Processing Systems (NeurIPS'23).
-
Tight conditions for when the NTK approximation is valid
(αβ) EB, Etai Littwin.
Transactions on Machine Learning Research (TMLR).
-
SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics
(αβ) Emmanuel Abbe, EB, Theodor Misiakiewicz.
Conference on Learning Theory (COLT'23).
-
GULP: a prediction-based metric between representations
EB*, Hannah Lawrence*, George Stepaniants*, Philippe Rigollet.
Conference on Neural Information Processing Systems (NeurIPS'22).
Selected as oral (top 8% accepted papers)
-
On the non-universality of deep learning: quantifying the cost of symmetry
(αβ) Emmanuel Abbe, EB.
Conference on Neural Information Processing Systems (NeurIPS'22).
-
The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks
(αβ) Emmanuel Abbe, EB, Theodor Misiakiewicz.
Conference on Learning Theory (COLT'22).
-
The staircase property: How hierarchical structure can guide deep learning
(αβ) Emmanuel Abbe, EB, Matthew Brennan, Guy Bresler, Dheeraj Nagaraj.
Conference on Neural Information Processing Systems (NeurIPS'21).
-
Chow-Liu++: Optimal Prediction-Centric Learning of Tree Ising Models
(αβ) EB, Guy Bresler, Frederic Koehler.
Foundations of Computer Science (FOCS'21).
-
Sample-Efficient Active Learning of Causal Trees
Kristjan Greenewald*, Dmitriy Katz-Rogozhnikov*, Karthikeyan Shanmugam*, Sara Magliacane, Murat Kocaoglu, EB, Guy Bresler.
Conference on Neural Information Processing Systems (NeurIPS'19).
-
Subadditivity Beyond Trees and the Chi-Squared Mutual Information
(αβ) Emmanuel Abbe, EB.
IEEE International Symposium on Information Theory (ISIT'19).
-
An Information-Percolation Bound for Spin Synchronization on General Graphs
(αβ) Emmanuel Abbe, EB.
Annals of Applied Probability (AAP).
-
Graph powering and spectral robustness
(αβ) Emmanuel Abbe, EB, Peter Ralli, Colin Sandon.
SIAM Journal on Mathematics of Data Science (SIMODS).
Optimal Transport
Miscellaneous