Africa
Simulation-Free Training of Neural ODEs on Paired Data
In this work, we investigate a method for simulation-free training of Neural Ordinary Differential Equations (NODEs) for learning deterministic mappings between paired data.
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
Core to our analysis is the reuse of minibatch in the gradient computation, which gives rise to higher-order information beyond correlational queries.
Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models
We study the task of learning SIMs in the agnostic (a.k.a.
Learning De-Biased Representations for Remote-Sensing Imagery
It is an unsupervised learning approach that can diversify minor class features based on the shared attributes with major classes, where the attributes are obtained by a simple step of clustering.
Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus
Additionally, methods that utilize the bisimulation metric for evaluating state discrepancies face a theory-practice gap due to improper approximations in metric learning, particularly struggling with hard exploration tasks.