Deep Learning
V ariance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies Oscar Li1, James Harrison, Jascha Sohl-Dickstein, Virginia Smith
First-order optimization methods are a foundational tool in machine learning.
Disentanglement via Latent Quantization
In disentangled representation learning, a model is asked to tease apart a dataset's
Learning Linear Causal Representations from Interventions under General Nonlinear Mixing Simon Buchholz
Therefore, it's important to study whether we can and also how to
Learning Linear Causal Representations from Interventions under General Nonlinear Mixing Simon Buchholz
Therefore, it's important to study whether we can and also how to
Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics Liming Wu
Markovian assumption makes current works immature in dynamics modeling.
Learning to Group Auxiliary Datasets for Molecule
The limited availability of annotations in small molecule datasets presents a challenge to machine learning models.
Energy Discrepancies: A Score-Independent Loss for Energy-Based Models
We propose a novel loss function called Energy Discrepancy (ED) which does not rely on the computation of scores or expensive Markov chain Monte Carlo.
Towards a Comprehensive Benchmark for High-Level Synthesis Targeted to FPGAs
Compiler directives in the form of pragmas play a crucial role in modifying the microarchitecture within the HLS framework. However, the number of possible microarchitectures grows exponentially with the number of pragmas.