Search Results for author: Carla Gomes

Found 22 papers, 8 papers with code

Deep Reasoning Networks for Unsupervised Pattern De-mixing with Constraint Reasoning

no code implementations ICML 2020 Di Chen, Yiwei Bai, Wenting Zhao, Sebastian Ament, John Gregoire, Carla Gomes

We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with constraint reasoning for solving pattern de-mixing problems, typically in an unsupervised or very-weakly-supervised setting.

Xtal2DoS: Attention-based Crystal to Sequence Learning for Density of States Prediction

no code implementations3 Feb 2023 Junwen Bai, Yuanqi Du, Yingheng Wang, Shufeng Kong, John Gregoire, Carla Gomes

Modern machine learning techniques have been extensively applied to materials science, especially for property prediction tasks.

Property Prediction

Structure-based Drug Design with Equivariant Diffusion Models

1 code implementation24 Oct 2022 Arne Schneuing, Yuanqi Du, Charles Harris, Arian Jamasb, Ilia Igashov, Weitao Du, Tom Blundell, Pietro Lió, Carla Gomes, Max Welling, Michael Bronstein, Bruno Correia

Structure-based drug design (SBDD) aims to design small-molecule ligands that bind with high affinity and specificity to pre-determined protein targets.


Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning

no code implementations28 Jun 2022 Dieqiao Feng, Carla Gomes, Bart Selman

To better understand why these approaches work, we studied the interplay of the policy and value networks of DNN-based best-first search on Sokoban and show the surprising effectiveness of the policy network, further enhanced by the value network, as a guiding heuristic for the search.

Scalable First-Order Bayesian Optimization via Structured Automatic Differentiation

1 code implementation16 Jun 2022 Sebastian Ament, Carla Gomes

To improve the performance of BO, prior work suggested incorporating gradient information into a Gaussian process surrogate of the objective, giving rise to kernel matrices of size $nd \times nd$ for $n$ observations in $d$ dimensions.

Bayesian Optimization

Contrastively Disentangled Sequential Variational Autoencoder

1 code implementation NeurIPS 2021 Junwen Bai, Weiran Wang, Carla Gomes

We propose a novel sequence representation learning method, named Contrastively Disentangled Sequential Variational Autoencoder (C-DSVAE), to extract and separate the static (time-invariant) and dynamic (time-variant) factors in the latent space.

Representation Learning

Sparse Bayesian Learning via Stepwise Regression

1 code implementation11 Jun 2021 Sebastian Ament, Carla Gomes

Herein, we propose a coordinate ascent algorithm for SBL termed Relevance Matching Pursuit (RMP) and show that, as its noise variance parameter goes to zero, RMP exhibits a surprising connection to Stepwise Regression.

feature selection regression

HOT-VAE: Learning High-Order Label Correlation for Multi-Label Classification via Attention-Based Variational Autoencoders

no code implementations9 Mar 2021 Wenting Zhao, Shufeng Kong, Junwen Bai, Daniel Fink, Carla Gomes

This in turn leads to a challenging and long-standing problem in the field of computer science - how to perform ac-curate multi-label classification with hundreds of labels?

Multi-Label Classification

Evaluating Multi-label Classifiers with Noisy Labels

no code implementations16 Feb 2021 Wenting Zhao, Carla Gomes

In the real world, it is more common to deal with noisy datasets than clean datasets, given how modern datasets are labeled by a large group of annotators on crowdsourcing platforms, but little attention has been given to evaluating multi-label classifiers with noisy labels.

Multi-Label Classification

Understanding Decoupled and Early Weight Decay

no code implementations27 Dec 2020 Johan Bjorck, Kilian Weinberger, Carla Gomes

We also show how the growth of network weights is heavily influenced by the dataset and its generalization properties.

Efficient Projection Algorithms onto the Weighted l1 Ball

no code implementations7 Sep 2020 Guillaume Perez, Sebastian Ament, Carla Gomes, Michel Barlaud

In this paper we propose three new efficient algorithms for projecting any vector of finite length onto the weighted $\ell_1$ ball.

BIG-bench Machine Learning feature selection

Disentangled Variational Autoencoder based Multi-Label Classification with Covariance-Aware Multivariate Probit Model

1 code implementation12 Jul 2020 Junwen Bai, Shufeng Kong, Carla Gomes

The decoder of MPVAE takes in the samples from the embedding spaces and models the joint distribution of output targets under a Multivariate Probit model by learning a shared covariance matrix.

General Classification Multi-Label Classification +1

Star-Convexity in Non-Negative Matrix Factorization

no code implementations25 Sep 2019 Johan Bjorck, Carla Gomes, Kilian Weinberger

Non-negative matrix factorization (NMF) is a highly celebrated algorithm for matrix decomposition that guarantees strictly non-negative factors.

Exponentially-Modified Gaussian Mixture Model: Applications in Spectroscopy

no code implementations14 Feb 2019 Sebastian Ament, John Gregoire, Carla Gomes

In particular, we demonstrate the effectiveness of PMF in conjunction with the EMG mixture model on synthetic data and two real-world applications: X-ray diffraction and Raman spectroscopy.


Understanding Batch Normalization

no code implementations NeurIPS 2018 Johan Bjorck, Carla Gomes, Bart Selman, Kilian Q. Weinberger

Batch normalization (BN) is a technique to normalize activations in intermediate layers of deep neural networks.

End-to-End Refinement Guided by Pre-trained Prototypical Classifier

1 code implementation7 May 2018 Junwen Bai, Zihang Lai, Runzhe Yang, Yexiang Xue, John Gregoire, Carla Gomes

We propose imitation refinement, a novel approach to refine imperfect input patterns, guided by a pre-trained classifier incorporating prior knowledge from simulated theoretical data, such that the refined patterns imitate the ideal data.

Deep Multi-Species Embedding

no code implementations28 Sep 2016 Di Chen, Yexiang Xue, Shuo Chen, Daniel Fink, Carla Gomes

Additionally, we demonstrate the benefit of using a deep neural network to extract features within the embedding and show how they improve the predictive performance of species distribution modelling.

Pattern Decomposition with Complex Combinatorial Constraints: Application to Materials Discovery

no code implementations27 Nov 2014 Stefano Ermon, Ronan Le Bras, Santosh K. Suram, John M. Gregoire, Carla Gomes, Bart Selman, Robert B. van Dover

Identifying important components or factors in large amounts of noisy data is a key problem in machine learning and data mining.

Cannot find the paper you are looking for? You can Submit a new open access paper.