Self-Supervised Learning is Approximately Supervised Learning
Preprint, arXiv, 2025
Publications
Preprints
DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
Preprint, arXiv, 2025
The Fair Language Model Paradox
Preprint, arXiv, 2024
Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent
Preprint, arXiv, 2023
Generalization Bounds for Transfer Learning with Pretrained Classifiers
Preprint, arXiv, 2022
Publications at Top-Tier Venues
Formation of Representations in Neural Networks
International Conference on Learning Representations (ICLR), 2025 Spotlight
Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference
International Conference on Learning Representations (ICLR), 2025
SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network
Conference on Parsimony and Learning (CPAL), 2025
NeurIPS Workshop on Mathematics of Modern Machine Learning (M3L), 2024
On the Power of Decision Trees in Auto-Regressive Language Modeling
Neural Information Processing Systems (NeurIPS), 2024
Norm-Based Generalization Bounds for Sparse Neural Networks
Neural Information Processing Systems (NeurIPS), 2023
Reverse Engineering Self-Supervised Learning
Neural Information Processing Systems (NeurIPS), 2023
Comparative Generalization Bounds for Deep Neural Networks
Transactions on Machine Learning Research (TMLR), 2023
Feature Learning in Deep Classifiers Through Intermediate Neural Collapse
International Conference on Machine Learning (ICML), 2023
Exploring the Approximation Capabilities of Multiplicative Neural Networks for Smooth Functions
Transactions on Machine Learning Research (TMLR), 2023
Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models
European Conference on Computer Vision (ECCV), 2022
On the Role of Neural Collapse in Transfer Learning
International Conference on Learning Representations (ICLR), 2022
Meta Internal Learning
Neural Information Processing Systems (NeurIPS), 2021
On Random Kernels of Residual Architectures
Uncertainty in Artificial Intelligence (UAI), 2021
Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs
Journal of Machine Learning Research (JMLR), 2021
Evaluation Metrics for Conditional Image Generation
International Journal of Computer Vision (IJCV), 2021
On the Modularity of Hypernetworks
Neural Information Processing Systems (NeurIPS), 2020
Oral
On Infinite-Width Hypernetworks
Neural Information Processing Systems (NeurIPS), 2020
Domain Intersection and Domain Difference
IEEE International Conference on Computer Vision (ICCV), 2019
Unsupervised Learning of the Set of Local Maxima
International Conference on Learning Representations (ICLR), 2019
Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer
International Conference on Learning Representations (ICLR), 2019
Estimating the Success of Unsupervised Image to Image Translation
European Conference on Computer Vision (ECCV), 2018
The Role of Minimal Complexity in Unsupervised Learning of Semantic Mappings
International Conference on Learning Representations (ICLR), 2018
Other Peer-Reviewed Publications
Distributed Speculative Inference of Large Language Models is Provably Faster
NeurIPS Workshop on Efficient Natural Language and Speech Processing (ENLSP), 2024 (PMLR)
Dynamics of Deep Classifiers Trained with the Square Loss: Normalization, Low Rank, Neural Collapse and Generalization Bounds
Research, 2023
Improved Generalization Bounds for Transfer Learning via Neural Collapse
ICML Workshop on Pretraining, 2022
On the Implicit Bias Towards Depth Minimization in Deep Neural Networks
Conference on the Mathematical Theory of Deep Neural Networks (DEEPMATH), 2022
Workshop on the Theory of Overparameterized Machine Learning (TOPML), 2022
Weakly Supervised Discovery of Semantic Attributes
Causal Learning and Reasoning (CLeaR), 2022
A Formal Approach to Explainability
Artificial Intelligence, Ethics and Society (AIES), 2019
Generalization Bounds for Cross-Domain Mapping with WGANs
NeurIPS Workshop on Integration of Deep Learning Theories, 2018
A Theoretical Framework for Deep Transfer Learning
Information and Inference: A Journal of the IMA (IMAIAI), 2016