Search Results for author:
Found 56 papers, 17 papers with code
Goodness-of-Fit of Attributed Probabilistic Graph Generative Models
Probabilistic generative models of graphs are important tools that enable representation and sampling.
Layer-Wise Feedback Alignment is Conserved in Deep Neural Networks
In the quest to enhance the efficiency and bio-plausibility of training deep neural networks, Feedback Alignment (FA), which replaces the backward pass weights with random matrices in the training process, has emerged as an alternative to traditional backpropagation.
No Bidding, No Regret: Pairwise-Feedback Mechanisms for Digital Goods and Data Auctions
The mechanism's novelty lies in using pairwise comparisons for eliciting information from the bidder, arguably easier for humans than assigning a numerical value.
Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
Double descent is a surprising phenomenon in machine learning, in which as the number of model parameters grows relative to the number of data, test error drops as models grow ever larger into the highly overparameterized (data undersampled) regime.
Target Conditioned Representation Independence (TCRI); From Domain-Invariant to Domain-General Representations
We propose a Target Conditioned Representation Independence (TCRI) objective for domain generalization.
Metric Elicitation; Moving from Theory to Practice
Specifically, we create a web-based ME interface and conduct a user study that elicits users' preferred metrics in a binary classification setting.
Batch Active Learning from the Perspective of Sparse Approximation
Active learning enables efficient model training by leveraging interactions between machine learning agents and human annotators.
Synthetic Power Analyses: Empirical Evaluation and Application to Cognitive Neuroimaging
We propose synthetic power analyses; a framework for estimating statistical power at various sample sizes, and empirically explore the performance of synthetic power analysis for sample size selection in cognitive neuroscience experiments.
Controllable Radiance Fields for Dynamic Face Synthesis
Recent work on 3D-aware image synthesis has achieved compelling results using advances in neural rendering.
ZenoPS: A Distributed Learning System Integrating Communication Efficiency and Security
Distributed machine learning is primarily motivated by the promise of increased computation power for accelerating training and mitigating privacy concerns.
A Reduction to Binary Approach for Debiasing Multiclass Datasets
We propose a novel reduction-to-binary (R2B) approach that enforces demographic parity for multiclass classification with non-binary sensitive attributes via a reduction to a sequence of binary debiasing tasks.
Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization
We propose a general theoretical framework proving that factors involving the model function class regularization are sufficient conditions for relative domain transferability.
Diagnosing failures of fairness transfer across distribution shift in real-world medical settings
Diagnosing and mitigating changes in model fairness under distribution shift is an important component of the safe deployment of machine learning in healthcare settings.
Joint Gaussian Graphical Model Estimation: A Survey
Graphs from complex systems often share a partial underlying structure across domains while retaining individual features.
Secure Byzantine-Robust Distributed Learning via Clustering
Federated learning systems that jointly preserve Byzantine robustness and privacy have remained an open problem.
Optimizing Black-box Metrics with Iterative Example Weighting
We consider learning to optimize a classification metric defined by a black-box function of the confusion matrix.
Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation
Controllable semantic image editing enables a user to change entire image attributes with a few clicks, e. g., gradually making a summer scene look like it was taken in winter.
A Nonconvex Framework for Structured Dynamic Covariance Recovery
We prove a linear convergence rate up to a nontrivial statistical error for the proposed descent scheme and establish sample complexity guarantees for the estimator.
Quadratic Metric Elicitation for Fairness and Beyond
Metric elicitation is a recent framework for eliciting classification performance metrics that best reflect implicit user preferences based on the task and context.
CSER: Communication-efficient SGD with Error Reset
The scalability of Distributed Stochastic Gradient Descent (SGD) is today limited by communication bottlenecks.
Bayesian Coresets: Revisiting the Nonconvex Optimization Perspective
Bayesian coresets have emerged as a promising approach for implementing scalable Bayesian inference.
Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability
Knowledge transferability, or transfer learning, has been widely adopted to allow a pre-trained model in the source domain to be effectively adapted to downstream tasks in the target domain.
Towards a Deep Network Architecture for Structured Smoothness
We propose the Fixed Grouping Layer (FGL); a novel feedforward layer designed to incorporate the inductive bias of structured smoothness into a deep learning model.
Rich-Item Recommendations for Rich-Users: Exploiting Dynamic and Static Side Information
In this paper, we study the problem of recommendation system where the users and items to be recommended are rich data structures with multiple entity types and with multiple sources of side-information in the form of graphs.
Toward a Controllable Disentanglement Network
By exploring the real-valued space of the soft target representation, we are able to synthesize novel images with the designated properties.
Learning Controllable Disentangled Representations with Decorrelation Regularization
By exploiting the real-valued space of the soft target representations, we are able to synthesize novel images with the designated properties.
Local AdaAlter: Communication-Efficient Stochastic Gradient Descent with Adaptive Learning Rates
When scaling distributed training, the communication overhead is often the bottleneck.
Learning Sparse Distributions using Iterative Hard Thresholding
Iterative hard thresholding (IHT) is a projected gradient descent algorithm, known to achieve state of the art performance for a wide range of structured estimation problems, such as sparse inference.
Estimating Differential Latent Variable Graphical Models with Applications to Brain Connectivity
Differential graphical models are designed to represent the difference between the conditional dependence structures of two groups, thus are of particular interest for scientific investigation.
Consistent Classification with Generalized Metrics
We propose a framework for constructing and analyzing multiclass and multioutput classification metrics, i. e., involving multiple, possibly correlated multiclass labels.
Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
We then provide a mechanism to generate the smallest set of changes that will improve an individual's outcome.
Partially Linear Additive Gaussian Graphical Models
We propose a partially linear additive Gaussian graphical model (PLA-GGM) for the estimation of associations between random variables distorted by observed confounders.
Clustered Monotone Transforms for Rating Factorization
This non-linear transformation of the rating scale shatters the low-rank structure of the rating matrix, therefore resulting in a poor fit and consequentially, poor recommendations.
Interpreting Black Box Predictions using Fisher Kernels
Research in both machine learning and psychology suggests that salient examples can help humans to interpret learning models.
Joint Nonparametric Precision Matrix Estimation with Confounding
Empirical results are presented using simulated and real brain imaging data, which suggest that our approach improves precision matrix estimation, as compared to baselines, when confounding is present.
xGEMs: Generating Examplars to Explain Black-Box Models
This work proposes xGEMs or manifold guided exemplars, a framework to understand black-box classifier behavior by exploring the landscape of the underlying data manifold as data points cross decision boundaries.
Performance Metric Elicitation from Pairwise Classifier Comparisons
Given a binary prediction problem, which performance metric should the classifier optimize?
Binary Classification with Karmic, Threshold-Quasi-Concave Metrics
Complex performance measures, beyond the popular measure of accuracy, are increasingly being used in the context of binary classification.
Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerance
We present Zeno, a technique to make distributed machine learning, particularly Stochastic Gradient Descent (SGD), tolerant to an arbitrary number of faulty workers.
Phocas: dimensional Byzantine-resilient stochastic gradient descent
We propose a novel robust aggregation rule for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model.
Learning the Base Distribution in Implicit Generative Models
Popular generative model learning methods such as Generative Adversarial Networks (GANs), and Variational Autoencoders (VAE) enforce the latent representation to follow simple distributions such as isotropic Gaussian.
Generalized Byzantine-tolerant SGD
We propose three new robust aggregation rules for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model.
Hallucinating brains with artificial brains
Our classification results provide a quantitative evaluation of the quality of the generated images, and also serve as an additional contribution of this manuscript.
Dependent relevance determination for smooth and structured sparse regression
Our approach represents a hierarchical extension of the relevance determination framework, where we add a transformed Gaussian process to model the dependencies between the prior variances of regression weights.
Consistency Analysis for Binary Classification Revisited
Statistical learning theory is at an inflection point enabled by recent advances in understanding and optimizing a wide range of metrics.
Preference Completion from Partial Rankings
We propose a novel and efficient algorithm for the collaborative preference completion problem, which involves jointly estimating individualized rankings for a set of entities over a shared set of items, based on a limited number of observed affinity values.
Online Classification with Complex Metrics
The proposed framework is general, as it applies to both batch and online learning, and to both linear and non-linear models.
Information Projection and Approximate Inference for Structured Sparse Variables
Approximate inference via information projection has been recently introduced as a general-purpose approach for efficient probabilistic inference given sparse variables.
A simple and provable algorithm for sparse diagonal CCA
Given two sets of variables, derived from a common set of samples, sparse Canonical Correlation Analysis (CCA) seeks linear combinations of a small number of variables in each set, such that the induced canonical variables are maximally correlated.
Generalized Linear Models for Aggregated Data
We consider a limiting case of generalized linear modeling when the target variables are only known up to permutation, and explore how this relates to permutation testing; a standard technique for assessing statistical dependency.
The Dynamics of Functional Brain Networks: Integrated Network States during Cognitive Function
Higher brain function relies upon the ability to flexibly integrate information across specialized communities of brain regions, however it is unclear how this mechanism manifests over time.
Neurons and Cognition
Optimal Decision-Theoretic Classification Using Non-Decomposable Performance Metrics
We provide a general theoretical analysis of expected out-of-sample utility, also referred to as decision-theoretic classification, for non-decomposable binary classification metrics such as F-measure and Jaccard coefficient.
False discovery rate smoothing
We also apply the method to a data set from an fMRI experiment on spatial working memory, where it detects patterns that are much more biologically plausible than those detected by standard FDR-controlling methods.
Methodology Applications Computation
A Constrained Matrix-Variate Gaussian Process for Transposable Data
Transposable data represents interactions among two sets of entities, and are typically represented as a matrix containing the known interaction values.
Constrained Bayesian Inference for Low Rank Multitask Learning
We present a novel approach for constrained Bayesian inference.
