12 citations · 30 across the 13 of their papers we have counts for
14 papers
Dangers of Bayesian Model Averaging under Covariate Shift
Pavel Izmailov, Patrick Nicholson, Sanae Lotfi +1
Approximate Bayesian inference for neural networks is considered a robust alternative to standard training, often providing good performance on out-of-distribution data. However, B…
Hypersuccinct Trees -- New universal tree source codes for optimal compressed tree data structures and range minima
J. Ian Munro, Patrick K. Nicholson, Louisa Seelbach Benkner +1
We present a new universal source code for distributions of unlabeled binary and ordinal trees that achieves optimal compression to within lower order terms for all tree sources co…
Any-k: Anytime Top-k Tree Pattern Retrieval in Labeled Graphs
Xiaofeng Yang, Deepak Ajwani, Wolfgang Gatterbauer +3
Many problems in areas as diverse as recommendation systems, social network analysis, semantic search, and distributed root cause analysis can be modeled as pattern search on label…
Optimal Query Time for Encoding Range Majority
Pawel Gawrychowski, Patrick K. Nicholson
We revisit the range -majority problem, which asks us to preprocess an array for a fixed value of , such that for any query range we can return a…
Optimal Distance Labeling Schemes for Trees
Ofer Freedman, Paweł Gawrychowski, Patrick K. Nicholson +1
Labeling schemes seek to assign a short label to each node in a network, so that a function on two nodes can be computed by examining their labels alone. For the particular case of…
Distributed Entity Disambiguation with Per-Mention Learning
Tiep Mai, Bichen Shi, Patrick K. Nicholson +2
Entity disambiguation, or mapping a phrase to its canonical representation in a knowledge base, is a fundamental step in many natural language processing applications. Existing tec…