Search Results for author:
Found 43 papers, 12 papers with code
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-body systems, is a foundational problem in science.
E(3)-Equivariant Mesh Neural Networks
Triangular meshes are widely used to represent three-dimensional objects.
Symmetry Breaking and Equivariant Neural Networks
Using symmetry as an inductive bias in deep learning has been proven to be a principled approach for sample-efficient model design.
Lie Point Symmetry and Physics Informed Networks
Symmetries have been leveraged to improve the generalization of neural networks through different mechanisms from data augmentation to equivariant architectures.
Learning to Reach Goals via Diffusion
We present a novel perspective on goal-conditioned reinforcement learning by framing it within the context of denoising diffusion models.
Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks
We present a natural extension to E(n)-equivariant graph neural networks that uses multiple equivariant vectors per node.
Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
We approach this problem from the lens of Koopman theory, where the nonlinear dynamics of the environment can be linearized in a high-dimensional latent space.
On Diffusion Modeling for Anomaly Detection
By simplifying DDPM in application to anomaly detection, we are naturally led to an alternative approach called Diffusion Time Estimation (DTE).
Equivariant Networks for Crystal Structures
Supervised learning with deep models has tremendous potential for applications in materials science.
Equivariance with Learned Canonicalization Functions
Symmetry-based neural networks often constrain the architecture in order to achieve invariance or equivariance to a group of transformations.
Utility Theory for Sequential Decision Making
A yet stronger constraint simplifies the utility function for goal-seeking agents in the form of a difference in some function of states that we call potential functions.
SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks
While (message-passing) graph neural networks have clear limitations in approximating permutation-equivariant functions over graphs or general relational data, more expressive, higher-order graph neural networks do not scale to large graphs.
Transformation Coding: Simple Objectives for Equivariant Representations
We present a simple non-generative approach to deep representation learning that seeks equivariant deep embedding through simple objectives.
EqR: Equivariant Representations for Data-Efficient Reinforcement Learning
We study different notions of equivariance as an inductive bias in Reinforcement Learning (RL) and propose new mechanisms for recovering representations that are equivariant to both an agent’s action, and symmetry transformations of the state-action pairs.
Equivariant Heterogeneous Graph Networks
Many real-world datasets include multiple distinct types of entities and relations, and so they are naturally best represented by heterogeneous graphs.
Equivariant Networks for Pixelized Spheres
We show how to model this interplay using ideas from group theory, identify the equivariant linear maps, and introduce equivariant padding that respects these symmetries.
Equivariant Networks for Hierarchical Structures
While using invariant and equivariant maps, it is possible to apply deep learning to a range of primitive data structures, a formalism for dealing with hierarchy is lacking.
Equivariant Maps for Hierarchical Structures
While using invariant and equivariant maps, it is possible to apply deep learning to a range of primitive data structures, a formalism for dealing with hierarchy is lacking.
Universal Equivariant Multilayer Perceptrons
Group invariant and equivariant Multilayer Perceptrons (MLP), also known as Equivariant Networks, have achieved remarkable success in learning on a variety of data structures, such as sequences, images, sets, and graphs.
Incidence Networks for Geometric Deep Learning
Sparse incidence tensors can represent a variety of structured data.
Equivariant Entity-Relationship Networks
In this paper, we propose the Equivariant Entity-Relationship Network (EERN), which is a Multilayer Perceptron equivariant to the symmetry transformations of the Entity-Relationship model.
Improved Knowledge Graph Embedding using Background Taxonomic Information
Knowledge graphs are used to represent relational information in terms of triples.
Learning to Predict the Cosmological Structure Formation
We build a deep neural network, the Deep Density Displacement Model (hereafter D$^3$M), to predict the non-linear structure formation of the Universe from simple linear perturbation theory.
Subject2Vec: Generative-Discriminative Approach from a Set of Image Patches to a Vector
Our model consists of three mutually dependent modules which regulate each other: (1) a discriminative network that learns a fixed-length representation from local features and maps them to disease severity; (2) an attention mechanism that provides interpretability by focusing on the areas of the anatomy that contribute the most to the prediction task; and (3) a generative network that encourages the diversity of the local latent features.
Deep Models of Interactions Across Sets
In experiments, our models achieved surprisingly good generalization performance on this matrix extrapolation task, both within domains (e. g., new users and new movies drawn from the same distribution used for training) and even across domains (e. g., predicting music ratings after training on movies).
Ranked #3 on
Recommendation Systems
on YahooMusic Monti
Min-Max Propagation
We study the application of min-max propagation, a variation of belief propagation, for approximate min-max inference in factor graphs.
Estimating Cosmological Parameters from the Dark Matter Distribution
A major approach to estimating the cosmological parameters is to use the large-scale matter distribution of the Universe.
Deep Sets
Our main theorem characterizes the permutation invariant functions and provides a family of functions to which any permutation invariant objective function must belong.
CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
We find on our simulated data set that for a rejection rate of non-lenses of 99%, a completeness of 90% can be achieved for lenses with Einstein radii larger than 1. 4" and S/N larger than 20 on individual $g$-band LSST exposures.
Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Astrophysics of Galaxies
Equivariance Through Parameter-Sharing
We propose to study equivariance in deep neural networks through parameter symmetries.
Deep Learning with Sets and Point Clouds
We introduce a simple permutation equivariant layer for deep learning with set structure. This type of layer, obtained by parameter-sharing, has a simple implementation and linear-time complexity in the size of each set.
Annealing Gaussian into ReLU: a New Sampling Strategy for Leaky-ReLU RBM
Due to numerical stability and quantifiability of the likelihood, RBM is commonly used with Bernoulli units.
Enabling Dark Energy Science with Deep Generative Models of Galaxy Images
To this end, we study the application of deep conditional generative models in generating realistic galaxy images.
Stochastic Neural Networks with Monotonic Activation Functions
We propose a Laplace approximation that creates a stochastic unit from any smooth monotonic activation function, using only Gaussian noise.
Embedding Inference for Structured Multilabel Prediction
A key bottleneck in structured output prediction is the need for inference during training and testing, usually requiring some form of dynamic programming.
Boolean Matrix Factorization and Noisy Completion via Message Passing
Boolean matrix factorization and Boolean matrix completion from noisy observations are desirable unsupervised data-analysis methods due to their interpretability, but hard to perform due to their NP-hardness.
Message Passing and Combinatorial Optimization
We contribute to three classes of approximations that improve BP for loopy graphs A) loop correction techniques; B) survey propagation, another message passing technique that surpasses BP in some settings; and C) hybrid methods that interpolate between deterministic message passing and Markov Chain Monte Carlo inference.
Revisiting Algebra and Complexity of Inference in Graphical Models
This paper studies the form and complexity of inference in graphical models using the abstraction offered by algebraic structures.
Accurate, fully-automated NMR spectral profiling for metabolomics
This information can be extracted from a biofluid's NMR spectrum.
Augmentative Message Passing for Traveling Salesman Problem and Graph Partitioning
The cutting plane method is an augmentative constrained optimization procedure that is often used with continuous-domain optimization techniques such as linear and convex programs.
Training Restricted Boltzmann Machine by Perturbation
During the learning, to produce a sample from the current model, we start from a training data and descend in the energy landscape of the "perturbed model", for a fixed number of steps, or until a local optima is reached.
Perturbed Message Passing for Constraint Satisfaction Problems
We introduce an efficient message passing scheme for solving Constraint Satisfaction Problems (CSPs), which uses stochastic perturbation of Belief Propagation (BP) and Survey Propagation (SP) messages to bypass decimation and directly produce a single satisfying assignment.
