Search Results for author:
Found 7 papers, 0 papers with code
Privately Fine-Tuning Large Language Models with Differential Privacy
Differential privacy (DP) provides a rigorous framework that allows adding noise in the process of training or fine-tuning LLMs such that extracting the training data becomes infeasible (i. e., with a cryptographically small success probability).
Network-level Safety Metrics for Overall Traffic Safety Assessment: A Case Study
To bridge these two perspectives, we define a new set of network-level safety metrics (NSM) to assess the overall safety profile of traffic flow by processing imagery taken by RSU cameras.
Sequential Bayesian Experimental Design with Variable Cost Structure
As a result, many algorithms utilize MI bounds as proxies that lack regret-style guarantees.
Lightweight Data Fusion with Conjugate Mappings
We present an approach to data fusion that combines the interpretability of structured probabilistic graphical models with the flexibility of neural networks.
A Robust Approach to Sequential Information Theoretic Planning
In many sequential planning applications a natural approach to generating high quality plans is to maximize an information reward such as mutual information (MI).
Multiscale Semi-Markov Dynamics for Intracortical Brain-Computer Interfaces
We propose a dynamic Bayesian network that includes the on-screen goal position as part of its latent state, and thus allows the person’s intended angle of movement to be aggregated over a much longer history of neural activity.
Minimization of Continuous Bethe Approximations: A Positive Variation
We develop convergent minimization algorithms for Bethe variational approximations which explicitly constrain marginal estimates to families of valid distributions.
