no code implementations • 3 Apr 2024 • Gabriel Loaiza-Ganem, Brendan Leigh Ross, Rasa Hosseinzadeh, Anthony L. Caterini, Jesse C. Cresswell
This manifold lens provides both clarity as to why some DGMs (e. g. diffusion models and some generative adversarial networks) empirically surpass others (e. g. likelihood-based models such as variational autoencoders, normalizing flows, or energy-based models) at sample generation, and guidance for devising more performant DGMs.
1 code implementation • 27 Mar 2024 • Hamidreza Kamkari, Brendan Leigh Ross, Jesse C. Cresswell, Anthony L. Caterini, Rahul G. Krishnan, Gabriel Loaiza-Ganem
We also show that this scenario can be identified through local intrinsic dimension (LID) estimation, and propose a method for OOD detection which pairs the likelihoods and LID estimates obtained from a pre-trained DGM.
1 code implementation • 24 Jan 2024 • Jesse C. Cresswell, Yi Sui, Bhargava Kumar, Noël Vouitsis
In response to everyday queries, humans explicitly signal uncertainty and offer alternative answers when they are unsure.
1 code implementation • 15 Dec 2023 • Noël Vouitsis, Zhaoyan Liu, Satya Krishna Gorti, Valentin Villecroze, Jesse C. Cresswell, Guangwei Yu, Gabriel Loaiza-Ganem, Maksims Volkovs
The goal of multimodal alignment is to learn a single latent space that is shared between multimodal inputs.
1 code implementation • 11 Oct 2023 • Yi Sui, Tongzi Wu, Jesse C. Cresswell, Ga Wu, George Stein, Xiao Shi Huang, Xiaochen Zhang, Maksims Volkovs
Self-supervised representation learning~(SSRL) has advanced considerably by exploiting the transformation invariance assumption under artificially designed data augmentations.
no code implementations • 14 Jun 2023 • Jiapeng Wu, Atiyeh Ashari Ghomi, David Glukhov, Jesse C. Cresswell, Franziska Boenisch, Nicolas Papernot
Differential privacy and randomized smoothing are effective defenses that provide certifiable guarantees for each of these threats, however, it is not well understood how implementing either defense impacts the other.
2 code implementations • NeurIPS 2023 • George Stein, Jesse C. Cresswell, Rasa Hosseinzadeh, Yi Sui, Brendan Leigh Ross, Valentin Villecroze, Zhaoyan Liu, Anthony L. Caterini, J. Eric T. Taylor, Gabriel Loaiza-Ganem
Comparing to 17 modern metrics for evaluating the overall performance, fidelity, diversity, rarity, and memorization of generative models, we find that the state-of-the-art perceptual realism of diffusion models as judged by humans is not reflected in commonly reported metrics such as FID.
1 code implementation • 30 Nov 2022 • Gabriel Loaiza-Ganem, Brendan Leigh Ross, Luhuan Wu, John P. Cunningham, Jesse C. Cresswell, Anthony L. Caterini
Likelihood-based deep generative models have recently been shown to exhibit pathological behaviour under the manifold hypothesis as a consequence of using high-dimensional densities to model data with low-dimensional structure.
no code implementations • 23 Nov 2022 • Jesse C. Cresswell, Brendan Leigh Ross, Gabriel Loaiza-Ganem, Humberto Reyes-Gonzalez, Marco Letizia, Anthony L. Caterini
Precision measurements and new physics searches at the Large Hadron Collider require efficient simulations of particle propagation and interactions within the detectors.
no code implementations • 12 Oct 2022 • Yi Sui, Junfeng Wen, Yenson Lau, Brendan Leigh Ross, Jesse C. Cresswell
In the traditional federated learning setting, a central server coordinates a network of clients to train one global model.
1 code implementation • 6 Jul 2022 • Bradley C. A. Brown, Anthony L. Caterini, Brendan Leigh Ross, Jesse C. Cresswell, Gabriel Loaiza-Ganem
Assuming that data lies on a single manifold implies intrinsic dimension is identical across the entire data space, and does not allow for subregions of this space to have a different number of factors of variation.
1 code implementation • 22 Jun 2022 • Brendan Leigh Ross, Gabriel Loaiza-Ganem, Anthony L. Caterini, Jesse C. Cresswell
We then learn the probability density within $\mathcal{M}$ with a constrained energy-based model, which employs a constrained variant of Langevin dynamics to train and sample from the learned manifold.
1 code implementation • 15 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.
2 code implementations • 14 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.
1 code implementation • 22 Nov 2021 • Shivam Kalra, Junfeng Wen, Jesse C. Cresswell, Maksims Volkovs, Hamid R. Tizhoosh
Institutions in highly regulated domains such as finance and healthcare often have restrictive rules around data sharing.
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.
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.