Search Results for author:
Found 15 papers, 2 papers with code
Boosting AND/OR-Based Computational Protein Design: Dynamic Heuristics and Generalizable UFO
Scientific computing has experienced a surge empowered by advancements in technologies such as neural networks.
Design Amortization for Bayesian Optimal Experimental Design
Bayesian optimal experimental design is a sub-field of statistics focused on developing methods to make efficient use of experimental resources.
Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks
On a set of 26 benchmark Atari environments, MeanQ outperforms all tested baselines, including the best available baseline, SUNRISE, at 100K interaction steps in 16/26 environments, and by 68% on average.
NeuroBE: NN Approximations to Bucket Elimination
A major limiting factor in graphical model inference is the complexity of computing the partition function.
Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates
Under the belief that $\beta$ is closely related to the (state dependent) model uncertainty, Entropy Regularized Q-Learning (EQL) further introduces a principled scheduling of $\beta$ by maintaining a collection of the model parameters that characterizes model uncertainty.
Active learning with RESSPECT: Resource allocation for extragalactic astronomical transients
The Recommendation System for Spectroscopic follow-up (RESSPECT) project aims to enable the construction of optimized training samples for the Rubin Observatory Legacy Survey of Space and Time (LSST), taking into account a realistic description of the astronomical data environment.
Accelerating Dynamic Programs via Nested Benders Decomposition with Application to Multi-Person Pose Estimation
We present a novel approach to solve dynamic programs (DP), which are frequent in computer vision, on tree-structured graphs with exponential node state space.
ContextNet: Deep learning for Star Galaxy Classification
Our particular motivation is star galaxy classification for ground based optical surveys.
Learning Infinite RBMs with Frank-Wolfe
In this work, we propose an infinite restricted Boltzmann machine~(RBM), whose maximum likelihood estimation~(MLE) corresponds to a constrained convex optimization.
Multi-Person Pose Estimation via Column Generation
We give a novel integer program formulation of the multi-person pose estimation problem, in which variables correspond to assignments of parts in the image to poses in a two-tier, hierarchical way.
Belief Propagation in Conditional RBMs for Structured Prediction
We demonstrate that, in both maximum likelihood and max-margin learning, training conditional RBMs with BP as the inference routine can provide significantly better results than current state-of-the-art CD methods on structured prediction problems.
Decomposition Bounds for Marginal MAP
Marginal MAP inference involves making MAP predictions in systems defined with latent variables or missing information.
Distributed Estimation, Information Loss and Exponential Families
Distributed learning of probabilistic models from multiple data repositories with minimum communication is increasingly important.
Marginal Structured SVM with Hidden Variables
In this work, we propose the marginal structured SVM (MSSVM) for structured prediction with hidden variables.
Variational Algorithms for Marginal MAP
The marginal maximum a posteriori probability (MAP) estimation problem, which calculates the mode of the marginal posterior distribution of a subset of variables with the remaining variables marginalized, is an important inference problem in many models, such as those with hidden variables or uncertain parameters.
