Search Results for author:
Found 22 papers, 8 papers with code
Pattern Decomposition with Complex Combinatorial Constraints: Application to Materials Discovery
Identifying important components or factors in large amounts of noisy data is a key problem in machine learning and data mining.
Deep Multi-Species Embedding
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.
Scalable Relaxations of Sparse Packing Constraints: Optimal Biocontrol in Predator-Prey Network
Cascades represent rapid changes in networks.
End-to-End Refinement Guided by Pre-trained Prototypical Classifier
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.
Understanding Batch Normalization
Batch normalization (BN) is a technique to normalize activations in intermediate layers of deep neural networks.
Exponentially-Modified Gaussian Mixture Model: Applications in Spectroscopy
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.
Tackling Climate Change with Machine Learning
Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help.
Star-Convexity in Non-Negative Matrix Factorization
Non-negative matrix factorization (NMF) is a highly celebrated algorithm for matrix decomposition that guarantees strictly non-negative factors.
Disentangled Variational Autoencoder based Multi-Label Classification with Covariance-Aware Multivariate Probit Model
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.
Efficient Projection Algorithms onto the Weighted l1 Ball
In this paper we propose three new efficient algorithms for projecting any vector of finite length onto the weighted $\ell_1$ ball.
Understanding Decoupled and Early Weight Decay
We also show how the growth of network weights is heavily influenced by the dataset and its generalization properties.
Evaluating Multi-label Classifiers with Noisy Labels
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.
HOT-VAE: Learning High-Order Label Correlation for Multi-Label Classification via Attention-Based Variational Autoencoders
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?
Sparse Bayesian Learning via Stepwise Regression
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.
Contrastively Disentangled Sequential Variational Autoencoder
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.
Constrained Machine Learning: The Bagel Framework
Machine learning models are widely used for real-world applications, such as document analysis and vision.
Scalable First-Order Bayesian Optimization via Structured Automatic Differentiation
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.
Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning
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.
Structure-based Drug Design with Equivariant Diffusion Models
Structure-based drug design (SBDD) aims to design small-molecule ligands that bind with high affinity and specificity to pre-determined protein targets.
Xtal2DoS: Attention-based Crystal to Sequence Learning for Density of States Prediction
Modern machine learning techniques have been extensively applied to materials science, especially for property prediction tasks.
A new perspective on building efficient and expressive 3D equivariant graph neural networks
Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects.
Deep Reasoning Networks for Unsupervised Pattern De-mixing with Constraint Reasoning
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.
