175 citations · 995 across the 28 of their papers we have counts for
28 papers
TaskMet: Task-Driven Metric Learning for Model Learning
Dishank Bansal, Ricky T. Q. Chen, Mustafa Mukadam +1
Deep learning models are often deployed in downstream tasks that the training procedure may not be aware of. For example, models solely trained to achieve accurate predictions may…
On Kinetic Optimal Probability Paths for Generative Models
Neta Shaul, Ricky T. Q. Chen, Maximilian Nickel +2
Recent successful generative models are trained by fitting a neural network to an a-priori defined tractable probability density path taking noise to training examples. In this pap…
Multisample Flow Matching: Straightening Flows with Minibatch Couplings
Aram-Alexandre Pooladian, Heli Ben-Hamu, Carles Domingo-Enrich +3
Simulation-free methods for training continuous-time generative models construct probability paths that go between noise distributions and individual data samples. Recent works, su…
Distributional GFlowNets with Quantile Flows
Dinghuai Zhang, Ling Pan, Ricky T. Q. Chen +2
Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a stochastic policy for generating complex combinatorial structure through a s…
Flow Matching on General Geometries
Ricky T. Q. Chen, Yaron Lipman
We propose Riemannian Flow Matching (RFM), a simple yet powerful framework for training continuous normalizing flows on manifolds. Existing methods for generative modeling on manif…
Latent Discretization for Continuous-time Sequence Compression
Ricky T. Q. Chen, Matthew Le, Matthew Muckley +2
Neural compression offers a domain-agnostic approach to creating codecs for lossy or lossless compression via deep generative models. For sequence compression, however, most deep s…
Flow Matching for Generative Modeling
Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu +2
We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the not…
Neural Conservation Laws: A Divergence-Free Perspective
Jack Richter-Powell, Yaron Lipman, Ricky T. Q. Chen
We investigate the parameterization of deep neural networks that by design satisfy the continuity equation, a fundamental conservation law. This is enabled by the observation that…
Latent State Marginalization as a Low-cost Approach for Improving Exploration
Dinghuai Zhang, Aaron Courville, Yoshua Bengio +3
While the maximum entropy (MaxEnt) reinforcement learning (RL) framework -- often touted for its exploration and robustness capabilities -- is usually motivated from a probabilisti…
Unifying Generative Models with GFlowNets and Beyond
Dinghuai Zhang, Ricky T. Q. Chen, Nikolay Malkin +1
There are many frameworks for deep generative modeling, each often presented with their own specific training algorithms and inference methods. Here, we demonstrate the connections…
Matching Normalizing Flows and Probability Paths on Manifolds
Heli Ben-Hamu, Samuel Cohen, Joey Bose +5
Continuous Normalizing Flows (CNFs) are a class of generative models that transform a prior distribution to a model distribution by solving an ordinary differential equation (ODE).…
Theseus: A Library for Differentiable Nonlinear Optimization
Luis Pineda, Taosha Fan, Maurizio Monge +10
We present Theseus, an efficient application-agnostic open source library for differentiable nonlinear least squares (DNLS) optimization built on PyTorch, providing a common framew…
Semi-Discrete Normalizing Flows through Differentiable Tessellation
Ricky T. Q. Chen, Brandon Amos, Maximilian Nickel
Mapping between discrete and continuous distributions is a difficult task and many have had to resort to heuristical approaches. We propose a tessellation-based approach that direc…
Domain Adaptation via CycleGAN for Retina Segmentation in Optical Coherence Tomography
Ricky Chen, Timothy T. Yu, Gavin Xu +3
With the FDA approval of Artificial Intelligence (AI) for point-of-care clinical diagnoses, model generalizability is of the utmost importance as clinical decision-making must be d…
Fully differentiable optimization protocols for non-equilibrium steady states
Rodrigo A. Vargas-Hernández, Ricky T. Q. Chen, Kenneth A. Jung +1
In the case of quantum systems interacting with multiple environments, the time-evolution of the reduced density matrix is described by the Liouvillian. For a variety of physical o…
Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations
Winnie Xu, Ricky T. Q. Chen, Xuechen Li +1
We perform scalable approximate inference in continuous-depth Bayesian neural networks. In this model class, uncertainty about separate weights in each layer gives hidden units tha…
Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization
Chin-Wei Huang, Ricky T. Q. Chen, Christos Tsirigotis +1
Flow-based models are powerful tools for designing probabilistic models with tractable density. This paper introduces Convex Potential Flows (CP-Flow), a natural and efficient para…
Inverse design of dissipative quantum steady-states with implicit differentiation
Rodrigo A. Vargas-Hernández, Ricky T. Q. Chen, Kenneth A. Jung +1
Inverse design of a property that depends on the steady-state of an open quantum system is commonly done by grid-search type of methods. In this paper we present a new methodology…
Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering
Ricky T. Q. Chen, Dami Choi, Lukas Balles +2
Standard first-order stochastic optimization algorithms base their updates solely on the average mini-batch gradient, and it has been shown that tracking additional quantities such…
Neural Spatio-Temporal Point Processes
Ricky T. Q. Chen, Brandon Amos, Maximilian Nickel
We propose a new class of parameterizations for spatio-temporal point processes which leverage Neural ODEs as a computational method and enable flexible, high-fidelity models of di…
"Hey, that's not an ODE": Faster ODE Adjoints via Seminorms
Patrick Kidger, Ricky T. Q. Chen, Terry Lyons
Neural differential equations may be trained by backpropagating gradients via the adjoint method, which is another differential equation typically solved using an adaptive-step-siz…
SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
Yucen Luo, Alex Beatson, Mohammad Norouzi +4
Standard variational lower bounds used to train latent variable models produce biased estimates of most quantities of interest. We introduce an unbiased estimator of the log margin…
Scalable Gradients for Stochastic Differential Equations
Xuechen Li, Ting-Kam Leonard Wong, Ricky T. Q. Chen +1
The adjoint sensitivity method scalably computes gradients of solutions to ordinary differential equations. We generalize this method to stochastic differential equations, allowing…
Neural Networks with Cheap Differential Operators
Ricky T. Q. Chen, David Duvenaud
Gradients of neural networks can be computed efficiently for any architecture, but some applications require differential operators with higher time complexity. We describe a famil…