Deep learning has become the state-of-art tool in many applications, but the evaluation and
training of deep models can be time-consuming and computationally expensive. The …

Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse
set of candidates in an active learning context, with a training objective that makes them …

We examine the role of memorization in deep learning, drawing connections to capacity,
generalization, and adversarial robustness. While deep networks are capable of memorizing …

This paper is about the problem of learning a stochastic policy for generating an object (like
a molecular graph) from a sequence of actions, such that the probability of generating an …

In this paper we present the techniques used for the University of Montréal's team submissions
to the 2013 Emotion Recognition in the Wild Challenge. The challenge is to classify the …

Abstract Design of de novo biological sequences with desired properties, like protein and
DNA sequences, often involves an active loop with several rounds of molecule ideation and …

Generative flow networks (GFlowNets) are a family of algorithms that learn a generative policy
to sample discrete objects $ x $ with non-negative reward $ R (x) $. Learning objectives …

Generative flow networks (GFlowNets) are a method for learning a stochastic policy for
generating compositional objects, such as graphs or strings, from a given unnormalized density …

Generative flow networks (GFlowNets) are a family of algorithms for training a sequential
sampler of discrete objects under an unnormalized target density and have been successfully …

We study the problem of generating diverse candidates in the context of Multi-Objective
Optimization. In many applications of machine learning such as drug discovery and material …