Search Results for author: Jesse C. Cresswell

Found 7 papers, 5 papers with code

The Union of Manifolds Hypothesis and its Implications for Deep Generative Modelling

no code implementations6 Jul 2022 Bradley C. A. Brown, Anthony L. Caterini, Brendan Leigh Ross, Jesse C. Cresswell, Gabriel Loaiza-Ganem

We show that clustered DGMs can model multiple connected components with different intrinsic dimensions, and empirically outperform their non-clustered counterparts without increasing computational requirements.

Neural Implicit Manifold Learning for Topology-Aware Generative Modelling

no code implementations22 Jun 2022 Brendan Leigh Ross, Gabriel Loaiza-Ganem, Anthony L. Caterini, Jesse C. Cresswell

Natural data observed in $\mathbb{R}^n$ is often constrained to an $m$-dimensional manifold $\mathcal{M}$, where $m < n$.

Disparate Impact in Differential Privacy from Gradient Misalignment

1 code implementation15 Jun 2022 Maria S. Esipova, Atiyeh Ashari Ghomi, Yaqiao Luo, Jesse C. Cresswell

As machine learning becomes more widespread throughout society, aspects including data privacy and fairness must be carefully considered, and are crucial for deployment in highly regulated industries.

Fairness

Diagnosing and Fixing Manifold Overfitting in Deep Generative Models

1 code implementation14 Apr 2022 Gabriel Loaiza-Ganem, Brendan Leigh Ross, Jesse C. Cresswell, Anthony L. Caterini

We propose a class of two-step procedures consisting of a dimensionality reduction step followed by maximum-likelihood density estimation, and prove that they recover the data-generating distribution in the nonparametric regime, thus avoiding manifold overfitting.

Density Estimation Dimensionality Reduction

ProxyFL: Decentralized Federated Learning through Proxy Model Sharing

1 code implementation22 Nov 2021 Shivam Kalra, Junfeng Wen, Jesse C. Cresswell, Maksims Volkovs, Hamid R. Tizhoosh

The proposed method eliminates a significant limitation of canonical federated learning by allowing model heterogeneity; each participant can have a private model with any architecture.

Federated Learning whole slide images

Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows

1 code implementation NeurIPS 2021 Brendan Leigh Ross, Jesse C. Cresswell

Normalizing flows are generative models that provide tractable density estimation via an invertible transformation from a simple base distribution to a complex target distribution.

Density Estimation

C-Learning: Horizon-Aware Cumulative Accessibility Estimation

1 code implementation ICLR 2021 Panteha Naderian, Gabriel Loaiza-Ganem, Harry J. Braviner, Anthony L. Caterini, Jesse C. Cresswell, Tong Li, Animesh Garg

In order to address these limitations, we introduce the concept of cumulative accessibility functions, which measure the reachability of a goal from a given state within a specified horizon.

Continuous Control Motion Planning

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