Search Results for author:
Found 55 papers, 15 papers with code
Risk Assessment and Statistical Significance in the Age of Foundation Models
Using this framework, we formally develop a risk-aware approach for foundation model selection given guardrails quantified by specified metrics.
Auditing and Generating Synthetic Data with Controllable Trust Trade-offs
We present an auditing framework that offers a holistic assessment of synthetic datasets and AI models trained on them, centered around bias and discrimination prevention, fidelity to the real data, utility, robustness, and privacy preservation.
Effective Dynamics of Generative Adversarial Networks
Generative adversarial networks (GANs) are a class of machine-learning models that use adversarial training to generate new samples with the same (potentially very complex) statistics as the training samples.
Cloud-Based Real-Time Molecular Screening Platform with MolFormer
With the prospect of automating a number of chemical tasks with high fidelity, chemical language processing models are emerging at a rapid speed.
Learning with Stochastic Orders
Learning high-dimensional distributions is often done with explicit likelihood modeling or implicit modeling via minimizing integral probability metrics (IPMs).
Auditing Differential Privacy in High Dimensions with the Kernel Quantum Rényi Divergence
Differential privacy (DP) is the de facto standard for private data release and private machine learning.
Cycle Consistent Probability Divergences Across Different Spaces
Discrepancy measures between probability distributions are at the core of statistical inference and machine learning.
Physics-enhanced deep surrogates for PDEs
Many physics and engineering applications demand Partial Differential Equations (PDE) property evaluations that are traditionally computed with resource-intensive high-fidelity numerical solvers.
Tighter Sparse Approximation Bounds for ReLU Neural Networks
A well-known line of work (Barron, 1993; Breiman, 1993; Klusowski & Barron, 2018) provides bounds on the width $n$ of a ReLU two-layer neural network needed to approximate a function $f$ over the ball $\mathcal{B}_R(\mathbb{R}^d)$ up to error $\epsilon$, when the Fourier based quantity $C_f = \frac{1}{(2\pi)^{d/2}} \int_{\mathbb{R}^d} \|\xi\|^2 |\hat{f}(\xi)| \ d\xi$ is finite.
Large-Scale Chemical Language Representations Capture Molecular Structure and Properties
Models based on machine learning can enable accurate and fast molecular property predictions, which is of interest in drug discovery and material design.
Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics
Several works in implicit and explicit generative modeling empirically observed that feature-learning discriminators outperform fixed-kernel discriminators in terms of the sample quality of the models.
Measuring Generalization with Optimal Transport
Understanding the generalization of deep neural networks is one of the most important tasks in deep learning.
Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks
Gradient flows are a powerful tool for optimizing functionals in general metric spaces, including the space of probabilities endowed with the Wasserstein metric.
Fair Mixup: Fairness via Interpolation
Training classifiers under fairness constraints such as group fairness, regularizes the disparities of predictions between the groups.
Image Captioning as an Assistive Technology: Lessons Learned from VizWiz 2020 Challenge
Image captioning has recently demonstrated impressive progress largely owing to the introduction of neural network algorithms trained on curated dataset like MS-COCO.
Alleviating Noisy Data in Image Captioning with Cooperative Distillation
Image captioning systems have made substantial progress, largely due to the availability of curated datasets like Microsoft COCO or Vizwiz that have accurate descriptions of their corresponding images.
On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow
We then derive an explicit condition which ensures that gradient descent on the parameter space of the generator in gradient regularized $\mathrm{MMD}$ GAN is globally convergent to the target distribution.
Tabular Transformers for Modeling Multivariate Time Series
This results in two architectures for tabular time series: one for learning representations that is analogous to BERT and can be pre-trained end-to-end and used in downstream tasks, and one that is akin to GPT and can be used for generation of realistic synthetic tabular sequences.
Unbalanced Sobolev Descent
USD transports particles along gradient flows of the witness function of the Sobolev-Fisher discrepancy (advection step) and reweighs the mass of particles with respect to this witness function (reaction step).
Active learning of deep surrogates for PDEs: Application to metasurface design
Surrogate models for partial-differential equations are widely used in the design of meta-materials to rapidly evaluate the behavior of composable components.
Kernel Stein Generative Modeling
NCK is crucial for successful inference with SVGD in high dimension, as it adapts the kernel to the noise level of the score estimate.
Fast Mixing of Multi-Scale Langevin Dynamics under the Manifold Hypothesis
Recently, the task of image generation has attracted much attention.
Learning Implicit Text Generation via Feature Matching
Generative feature matching network (GFMN) is an approach for training implicit generative models for images by performing moment matching on features from pre-trained neural networks.
Nano-Material Configuration Design with Deep Surrogate Langevin Dynamics
We consider the problem of optimizing by sampling under multiple black-box constraints in nano-material design.
Improving Efficiency in Large-Scale Decentralized Distributed Training
Decentralized Parallel SGD (D-PSGD) and its asynchronous variant Asynchronous Parallel SGD (AD-PSGD) is a family of distributed learning algorithms that have been demonstrated to perform well for large-scale deep learning tasks.
Generative Modeling with Denoising Auto-Encoders and Langevin Sampling
We show that both DAE and DSM provide estimates of the score of the Gaussian smoothed population density, allowing us to apply the machinery of Empirical Processes.
Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets
Then we propose an adaptive variant of OSG named Optimistic Adagrad (OAdagrad) and reveal an \emph{improved} adaptive complexity $O\left(\epsilon^{-\frac{2}{1-\alpha}}\right)$, where $\alpha$ characterizes the growth rate of the cumulative stochastic gradient and $0\leq \alpha\leq 1/2$.
Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces
This paper focuses on the problem of unsupervised alignment of hierarchical data such as ontologies or lexical databases.
Sobolev Independence Criterion
In the kernel version we show that SIC can be cast as a convex optimization problem by introducing auxiliary variables that play an important role in feature selection as they are normalized feature importance scores.
A Decentralized Parallel Algorithm for Training Generative Adversarial Nets
Despite recent progress on decentralized algorithms for training deep neural networks, it remains unclear whether it is possible to train GANs in a decentralized manner.
Surrogate-Based Constrained Langevin Sampling With Applications to Optimal Material Configuration Design
We consider the problem of generating configurations that satisfy physical constraints for optimal material nano-pattern design, where multiple (and often conflicting) properties need to be simultaneously satisfied.
Wasserstein Style Transfer
Moreover interpolates between a content and a style image can be seen as geodesics in the Wasserstein Geometry.
Generative Feature Matching Networks
We propose a non-adversarial feature matching-based approach to train generative models.
Learning Implicit Generative Models by Matching Perceptual Features
Perceptual features (PFs) have been used with great success in tasks such as transfer learning, style transfer, and super-resolution.
Improved Adversarial Image Captioning
In this paper we study image captioning as a conditional GAN training, proposing both a context-aware LSTM captioner and co-attentive discriminator, which enforces semantic alignment between images and captions.
Implicit Kernel Learning
While learning the kernel in a data driven way has been investigated, in this paper we explore learning the spectral distribution of kernel via implicit generative models parametrized by deep neural networks.
Wasserstein Barycenter Model Ensembling
In this paper we propose to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein (W.) barycenters.
Sobolev Descent
We study a simplification of GAN training: the problem of transporting particles from a source to a target distribution.
Regularized Finite Dimensional Kernel Sobolev Discrepancy
We show in this note that the Sobolev Discrepancy introduced in Mroueh et al in the context of generative adversarial networks, is actually the weighted negative Sobolev norm $||.||_{\dot{H}^{-1}(\nu_q)}$, that is known to linearize the Wasserstein $W_2$ distance and plays a fundamental role in the dynamic formulation of optimal transport of Benamou and Brenier.
Adversarial Semantic Alignment for Improved Image Captions
When evaluated on OOC and MS-COCO benchmarks, we show that SCST-based training has a strong performance in both semantic score and human evaluation, promising to be a valuable new approach for efficient discrete GAN training.
Semi-Supervised Learning with IPM-based GANs: an Empirical Study
We present an empirical investigation of a recent class of Generative Adversarial Networks (GANs) using Integral Probability Metrics (IPM) and their performance for semi-supervised learning.
Sobolev GAN
We show that the Sobolev IPM compares two distributions in high dimensions based on weighted conditional Cumulative Distribution Functions (CDF) of each coordinate on a leave one out basis.
Fisher GAN
In this paper we introduce Fisher GAN which fits within the Integral Probability Metrics (IPM) framework for training GANs.
McGan: Mean and Covariance Feature Matching GAN
We introduce new families of Integral Probability Metrics (IPM) for training Generative Adversarial Networks (GAN).
Local Group Invariant Representations via Orbit Embeddings
We consider transformations that form a \emph{group} and propose an approach based on kernel methods to derive local group invariant representations.
Self-critical Sequence Training for Image Captioning
In this paper we consider the problem of optimizing image captioning systems using reinforcement learning, and show that by carefully optimizing our systems using the test metrics of the MSCOCO task, significant gains in performance can be realized.
Co-Occuring Directions Sketching for Approximate Matrix Multiply
We introduce co-occurring directions sketching, a deterministic algorithm for approximate matrix product (AMM), in the streaming model.
Learning with Group Invariant Features: A Kernel Perspective.
Our analysis bridges invariant feature learning with kernel methods, as we show that this feature map defines an expected Haar-integration kernel that is invariant to the specified group action.
Asymmetrically Weighted CCA And Hierarchical Kernel Sentence Embedding For Image & Text Retrieval
Joint modeling of language and vision has been drawing increasing interest.
Random Maxout Features
In this paper, we propose and study random maxout features, which are constructed by first projecting the input data onto sets of randomly generated vectors with Gaussian elements, and then outputing the maximum projection value for each set.
Learning with Group Invariant Features: A Kernel Perspective
Our analysis bridges invariant feature learning with kernel methods, as we show that this feature map defines an expected Haar integration kernel that is invariant to the specified group action.
Convex Learning of Multiple Tasks and their Structure
In this context a fundamental question is how to incorporate the tasks structure in the learning problem. We tackle this question by studying a general computational framework that allows to encode a-priori knowledge of the tasks structure in the form of a convex penalty; in this setting a variety of previously proposed methods can be recovered as special cases, including linear and non-linear approaches.
Deep Multimodal Learning for Audio-Visual Speech Recognition
In this paper, we present methods in deep multimodal learning for fusing speech and visual modalities for Audio-Visual Automatic Speech Recognition (AV-ASR).
Audio-Visual Speech Recognition
Automatic Speech Recognition
+3
Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines?
The standard approach to unconstrained face recognition in natural photographs is via a detection, alignment, recognition pipeline.
Multiclass Learning with Simplex Coding
In this paper we dicuss a novel framework for multiclass learning, defined by a suitable coding/decoding strategy, namely the simplex coding, that allows to generalize to multiple classes a relaxation approach commonly used in binary classification.
