8 papers
SCOPE Before You Sample: Conformal Scores Guide Posterior Exploration for Fast and Calibrated Bayesian Predictive Inference
Zahra Moslemi, Ziyi Liang, Babak Shahbaba
Bayesian predictive regions account for parameter uncertainty but can be poorly calibrated under model misspecification, even with expensive full MCMC. Cheaper approximations such…
ConformalHDC: Uncertainty-Aware Hyperdimensional Computing with Application to Neural Decoding
Ziyi Liang, Hamed Poursiami, Zhishun Yang +5
Hyperdimensional Computing (HDC) offers a computationally efficient paradigm for neuromorphic learning. Yet, it lacks rigorous uncertainty quantification, leading to open decision…
Heterogeneous Graph Alignment for Joint Reasoning and Interpretability
Zahra Moslemi, Ziyi Liang, Norbert Fortin +1
Multi-graph learning is crucial for extracting meaningful signals from collections of heterogeneous graphs. However, effectively integrating information across graphs with differin…
Neural-Inspired Posterior Approximation (NIPA)
Babak Shahbaba, Zahra Moslemi
Humans learn efficiently from their environment by engaging multiple interacting neural systems that support distinct yet complementary forms of control, including model-based (goa…
Meta Fusion: A Unified Framework For Multimodality Fusion with Mutual Learning
Ziyi Liang, Annie Qu, Babak Shahbaba
Developing effective multimodal data fusion strategies has become increasingly essential for improving the predictive power of statistical machine learning methods across a wide ra…
Reinforcement Learning for Individual Optimal Policy from Heterogeneous Data
Rui Miao, Babak Shahbaba, Annie Qu
Offline reinforcement learning (RL) aims to find optimal policies in dynamic environments in order to maximize the expected total rewards by leveraging pre-collected data. Learning…
Weakly-Supervised Multimodal Learning on MIMIC-CXR
Andrea Agostini, Daphné Chopard, Yang Meng +5
Multimodal data integration and label scarcity pose significant challenges for machine learning in medical settings. To address these issues, we conduct an in-depth evaluation of t…
Optimal Transport for Latent Integration with An Application to Heterogeneous Neuronal Activity Data
Yubai Yuan, Babak Shahbaba, Norbert Fortin +3
Detecting dynamic patterns of task-specific responses shared across heterogeneous datasets is an essential and challenging problem in many scientific applications in medical scienc…