Publications
Peer-Reviewed Papers
An Unbiased Method to Partition Diverse Neuronal Responses into Functional Ensembles Reveals Novel Population Dynamics During Social Behavior
Alexander Lin, Olga Dal Monte, Siqi Fan, Nicholas Fagan, Philip Putnam, Kay Tye, Steve Chang, Demba Ba, AZA Stephen Allsop
Under Review, 2023
An Efficient Algorithm for Clustered Multi-Task Compressive Sensing
Alexander Lin, Demba Ba
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024
[preprint]
Probabilistic Unrolling: Scalable, Inverse-Free Maximum Likelihood Estimation for Latent Gaussian Models
Alexander Lin, Bahareh Tolooshams, Yves Atchadé, Demba Ba
International Conference on Machine Learning (ICML), 2023
[official] [preprint] [poster]
How to Train Your FALCON: Learning Log-Concave Densities with Energy-Based Neural Networks
Alexander Lin, Demba Ba
Symposium on Advances in Approximate Bayesian Inference (AABI), 2023
Selected for Oral Presentation
[official] [poster]
Word-Level Explanations for Analyzing Bias in Text-to-Image Models
Alexander Lin*, Lucas Monteiro Paes*, Sree Harsha Tanneru*, Suraj Srinivas, Himabindu Lakkaraju (* equal contribution)
International Conference on Machine Learning (ICML) -- Workshop on Challenges of Deploying Generative AI, 2023
[official] [preprint] [poster]
Incorporating Knowledge of Plates in Batch Normalization Improves Generalization of Deep Learning for Microscopy Images
Alexander Lin, Alex X. Lu
Machine Learning in Computational Biology (MLCB), 2022
Selected for Oral Presentation
[official] [preprint] [code] [video]
Covariance-Free Sparse Bayesian Learning
Alexander Lin, Andrew H. Song, Berkin Bilgic, Demba Ba
IEEE Transactions on Signal Processing, 2022
[official] [preprint] [code]
Bayesian Sensitivity Encoding Enables Parameter-Free, Highly Accelerated Joint Multi-Contrast Reconstruction
Alexander Lin, Demba Ba, Berkin Bilgic
Annual Meeting of the International Society of Magnetic Resonance in Medicine (ISMRM), 2022
Selected for Oral Presentation
[official] [code]
High-Dimensional Sparse Bayesian Learning without Covariance Matrices
Alexander Lin, Andrew H. Song, Berkin Bilgic, Demba Ba
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022
[official] [preprint] [code] [slides]
Mixture Model Auto-Encoders: Deep Clustering through Dictionary Learning
Alexander Lin, Andrew H. Song, Demba Ba
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022
[official] [preprint] [code] [slides]
Accelerating Bayesian Compressed Sensing for Fast Multi-Contrast Reconstruction
Alexander Lin, Demba Ba, Berkin Bilgic
Annual Meeting of the International Society of Magnetic Resonance in Medicine (ISMRM), 2021
[official] [code]
Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems
Derek Chen, Howard Chen, Yi Yang, Alexander Lin, Zhou Yu
Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2021
[official] [preprint] [code] [blogpost]
Autoregressive Knowledge Distillation through Imitation Learning
Alexander Lin, Jeremy Wohlwend, Howard Chen, Tao Lei
Empirical Methods in Natural Language Processing (EMNLP), 2020
[official] [preprint] [code] [video]
Universal Causal Evaluation Engine: An API for Empirically Evaluating Causal Inference Models
Alexander Lin*, Amil Merchant*, Suproteem K. Sarkar*, Alexander D'Amour (* equal contribution)
Knowledge Discovery and Data Mining (KDD) -- Workshop on Causal Discovery, 2019
[official] [code]
Clustering Time Series with Nonlinear Dynamics: A Bayesian Non-Parametric and Particle-Based Approach
Alexander Lin, Yingzhuo Zhang, Jeremy Heng, Stephen A. Allsop, Kay M. Tye, Pierre E. Jacob, Demba Ba
International Conference on Artificial Intelligence and Statistics (AISTATS), 2019
[official] [preprint] [code]
Thesis
Model-Based Clustering of Time Series Exhibiting Nonlinear Dynamics
Alexander Lin
Supervised by Demba Ba and Pierre E. Jacob
A.B. Thesis, Harvard College
[official]