The proliferation of capable and efficient machine learning (ML) models marks one of the strongest methodological shifts in signal processing (SP) in its nearly 100-year history. ML models support the development of SP systems that represent complex, nonlinear relationships with high predictive accuracy. Adapting these...
Daniel Waxman, F. Llorente, Petar M. Djurić et al.· IEEE Signal Processing Magaz...· 0 citations
Localizing behavior to individual components of a language model is a central goal of mechanistic interpretability. However, scoring components one at a time misses context-dependent effects: a primary component can inhibit the activation of a backup, leading to issues with ranking components. Actual causality studies...
Sankaran Vaidyanathan, R. Urbaniak, Emily Bunnapradist et al.· 0 citations
The dynamics of cells, organisms, and fluids are often modeled as probability distributions evolving over time. Reconstructing and extrapolating this evolution from unpaired snapshots requires assumptions about the underlying process. Wasserstein gradient flows are a common choice, but they cannot describe conservative...
F. Sergeev, Markus Heinonen, Daniel Waxman et al.· 0 citations
Probabilistic Causal Impact (PCI) builds on actual causality and on Pearl's notions of probability of necessity and sufficiency, but recasts the question of explainability as an estimation problem on a probabilistic causal model that is easily approximated via Monte Carlo.
R. Urbaniak, Sam Witty, Daniel Waxman et al.· 1 citation
It is demonstrated that the stitching method achieves state-of-the-art performance across trajectory inference benchmarks, and unifies several existing methods and leads to a new particle-based method, stitching, that is simulation-free and robust to large gaps between observations.
Markus Heinonen, Yair Shenfeld, R. Baptista et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
