Search Results for author:
Found 12 papers, 6 papers with code
Utilization of domain knowledge to improve POMDP belief estimation
The partially observable Markov decision process (POMDP) framework is a common approach for decision making under uncertainty.
ClimaX: A foundation model for weather and climate
Most state-of-the-art approaches for weather and climate modeling are based on physics-informed numerical models of the atmosphere.
Machine Learning Approach to Polymerization Reaction Engineering: Determining Monomers Reactivity Ratios
Here, we demonstrate how machine learning enables the prediction of comonomers reactivity ratios based on the molecular structure of monomers.
Reliable Conditioning of Behavioral Cloning for Offline Reinforcement Learning
We study CWBC in the context of RvS (Emmons et al., 2021) and Decision Transformers (Chen et al., 2021), and show that CWBC significantly boosts their performance on various benchmarks.
Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling
We propose Transformer Neural Processes (TNPs), a new member of the NP family that casts uncertainty-aware meta learning as a sequence modeling problem.
A Simple and Scalable Tensor Completion Algorithm via Latent Invariant Constraint for Recommendation System
In this paper we provide a latent-variable formulation and solution to the recommender system (RS) problem in terms of a fundamental property that any reasonable solution should be expected to satisfy.
Tensor Completion with Provable Consistency and Fairness Guarantees for Recommender Systems
The framework and solution algorithms also generalize directly to tensors of arbitrary dimensions while maintaining computational complexity that is linear in problem size for fixed dimension d. In the context of recommender system (RS) applications, we prove that two reasonable properties that should be expected to hold for any solution to the RS problem are sufficient to permit uniqueness guarantees to be established within our framework.
Temporal Predictive Coding For Model-Based Planning In Latent Space
High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments.
Non-Markovian Predictive Coding For Planning In Latent Space
High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments.
Predictive Coding for Locally-Linear Control
High-dimensional observations and unknown dynamics are major challenges when applying optimal control to many real-world decision making tasks.
DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
The field of video compression has developed some of the most sophisticated and efficient compression algorithms known in the literature, enabling very high compressibility for little loss of information.
Image Colorization Using a Deep Convolutional Neural Network
In this paper, we present a novel approach that uses deep learning techniques for colorizing grayscale images.
