Search Results for author:
Found 10 papers, 3 papers with code
A Bayesian Unification of Self-Supervised Clustering and Energy-Based Models
Self-supervised learning is a popular and powerful method for utilizing large amounts of unlabeled data, for which a wide variety of training objectives have been proposed in the literature.
The Triad of Failure Modes and a Possible Way Out
We present a novel objective function for cluster-based self-supervised learning (SSL) that is designed to circumvent the triad of failure modes, namely representation collapse, cluster collapse, and the problem of invariance to permutations of cluster assignments.
Learning Symbolic Representations Through Joint GEnerative and DIscriminative Training
We introduce GEDI, a Bayesian framework that combines existing self-supervised learning objectives with likelihood-based generative models.
GEDI: GEnerative and DIscriminative Training for Self-Supervised Learning
Our analysis suggests a simple method for integrating self-supervised learning with generative models, allowing for the joint training of these two seemingly distinct approaches.
VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming
To the best of our knowledge, this work is the first to propose a general-purpose end-to-end framework integrating probabilistic logic programming into a deep generative model.
LSB: Local Self-Balancing MCMC in Discrete Spaces
We present the Local Self-Balancing sampler (LSB), a local Markov Chain Monte Carlo (MCMC) method for sampling in purely discrete domains, which is able to autonomously adapt to the target distribution and to reduce the number of target evaluations required to converge.
Leveraging Hidden Structure in Self-Supervised Learning
This work considers the problem of learning structured representations from raw images using self-supervised learning.
Coulomb Autoencoders
Learning the true density in high-dimensional feature spaces is a well-known problem in machine learning.
Training Feedforward Neural Networks with Standard Logistic Activations is Feasible
Training feedforward neural networks with standard logistic activations is considered difficult because of the intrinsic properties of these sigmoidal functions.
Efficient Training for Positive Unlabeled Learning
Positive unlabeled (PU) learning is useful in various practical situations, where there is a need to learn a classifier for a class of interest from an unlabeled data set, which may contain anomalies as well as samples from unknown classes.
