Search Results for author:
Found 6 papers, 5 papers with code
The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning
We consider a different lower bound on the MI consisting of an entropy and a reconstruction term (ER), and analyze the main MVSSL families through its lens.
LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood
We attempt to address that challenge by proposing a novel approach to the problem: Local Intrinsic Dimension estimation using approximate Likelihood (LIDL).
COIN++: Neural Compression Across Modalities
Neural compression algorithms are typically based on autoencoders that require specialized encoder and decoder architectures for different data modalities.
Expectation Programming: Adapting Probabilistic Programming Systems to Estimate Expectations Efficiently
We show that the standard computational pipeline of probabilistic programming systems (PPSs) can be inefficient for estimating expectations and introduce the concept of expectation programming to address this.
COIN: COmpression with Implicit Neural representations
We propose a new simple approach for image compression: instead of storing the RGB values for each pixel of an image, we store the weights of a neural network overfitted to the image.
Amortized Monte Carlo Integration
At runtime, samples are produced separately from each amortized proposal, before being combined to an overall estimate of the expectation.
