Search Results for author:
Found 17 papers, 10 papers with code
Decoupling Semantic Similarity from Spatial Alignment for Neural Networks
In this paper, we propose to solve this through semantic RSMs, which are invariant to spatial permutation.
Towards flexible perception with visual memory
Training a neural network is a monolithic endeavor, akin to carving knowledge into stone: once the process is completed, editing the knowledge in a network is nearly impossible, since all information is distributed across the network's weights.
Intriguing properties of generative classifiers
What is the best paradigm to recognize objects -- discriminative inference (fast but potentially prone to shortcut learning) or using a generative model (slow but potentially more robust)?
Ranked #1 on
Object Recognition
on shape bias
Text-to-Image Diffusion Models are Zero-Shot Classifiers
The key idea is using a diffusion model's ability to denoise a noised image given a text description of a label as a proxy for that label's likelihood.
Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths
We consider the problem of sampling transition paths between two given metastable states of a molecular system, e. g. a folded and unfolded protein or products and reactants of a chemical reaction.
Particle Dynamics for Learning EBMs
We accomplish this by viewing the evolution of the modeling distribution as (i) the evolution of the energy function, and (ii) the evolution of the samples from this distribution along some vector field.
Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent
We focus on the problem of efficient sampling and learning of probability densities by incorporating symmetries in probabilistic models.
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
Argmax Flows are defined by a composition of a continuous distribution (such as a normalizing flow), and an argmax function.
Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC
Hybrid Monte Carlo is a powerful Markov Chain Monte Carlo method for sampling from complex continuous distributions.
Argmax Flows: Learning Categorical Distributions with Normalizing Flows
This paper introduces a new method to define and train continuous distributions such as normalizing flows directly on categorical data, for example text and image segmentation.
Self Normalizing Flows
Efficient gradient computation of the Jacobian determinant term is a core problem in many machine learning settings, and especially so in the normalizing flow framework.
SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
Normalizing flows and variational autoencoders are powerful generative models that can represent complicated density functions.
A Positivstellensatz for Conditional SAGE Signomials
Recently, the conditional SAGE certificate has been proposed as a sufficient condition for signomial positivity over a convex set.
Tails of Lipschitz Triangular Flows
We investigate the ability of popular flow based methods to capture tail-properties of a target density by studying the increasing triangular maps used in these flow methods acting on a tractable source density.
Sum-of-Squares Polynomial Flow
Triangular map is a recent construct in probability theory that allows one to transform any source probability density function to any target density function.
Deep Homogeneous Mixture Models: Representation, Separation, and Approximation
At their core, many unsupervised learning models provide a compact representation of homogeneous density mixtures, but their similarities and differences are not always clearly understood.
Online and Distributed learning of Gaussian mixture models by Bayesian Moment Matching
The Gaussian mixture model is a classic technique for clustering and data modeling that is used in numerous applications.
