Search Results for author:
Found 45 papers, 14 papers with code
Scalable 3D Registration via Truncated Entry-wise Absolute Residuals
Given an input set of $3$D point pairs, the goal of outlier-robust $3$D registration is to compute some rotation and translation that align as many point pairs as possible.
A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)
Traditional recommender systems (RS) have used user-item rating histories as their primary data source, with collaborative filtering being one of the principal methods.
Stochastic Extragradient with Random Reshuffling: Improved Convergence for Variational Inequalities
The Stochastic Extragradient (SEG) method is one of the most popular algorithms for solving finite-sum min-max optimization and variational inequality problems (VIPs) appearing in various machine learning tasks.
Knowledge Pursuit Prompting for Zero-Shot Multimodal Synthesis
To address this question, we propose Knowledge Pursuit Prompting (KPP), a zero-shot framework that iteratively incorporates external knowledge to help generators produce reliable visual content.
Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
Our analysis shows that, during the early phase of training, neurons in the first layer try to align with either the positive data or the negative data, depending on its corresponding weight on the second layer.
Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models
In this paper, we propose a novel image clustering pipeline that leverages the powerful feature representation of large pre-trained models such as CLIP and cluster images effectively and efficiently at scale.
A Linearly Convergent GAN Inversion-based Algorithm for Reverse Engineering of Deceptions
In this paper, we build on prior work and propose a novel framework for reverse engineering of deceptions which supposes that the clean data lies in the range of a GAN.
The Ideal Continual Learner: An Agent That Never Forgets
We show that ICL unifies multiple well-established continual learning methods and gives new theoretical insights into the strengths and weaknesses of these methods.
Necessary and Sufficient Conditions for Simultaneous State and Input Recovery of Linear Systems with Sparse Inputs by $\ell_1$-Minimization
In this work, we provide (1) the first characterization of necessary and sufficient conditions for the existence and uniqueness of sparse inputs to an LDS, (2) the first necessary and sufficient conditions for a linear program to recover both an unknown initial state and a sparse input, and (3) simple, interpretable recovery conditions in terms of the LDS parameters.
Variational Information Pursuit for Interpretable Predictions
We then demonstrate that the IP strategy is the optimal solution to this problem.
On the Convergence of IRLS and Its Variants in Outlier-Robust Estimation
Outlier-robust estimation involves estimating some parameters (e. g., 3D rotations) from data samples in the presence of outliers, and is typically formulated as a non-convex and non-smooth problem.
On Utilizing Relationships for Transferable Few-Shot Fine-Grained Object Detection
However, obtaining a large amount of training annotations specific to a particular task, i. e., fine-grained annotations, is costly in practice.
Facial Tic Detection in Untrimmed Videos of Tourette Syndrome Patients
Behavioral therapy is the first-line treatment for patients with TS, and it helps patients raise awareness about tic occurrence as well as develop tic inhibition strategies.
Towards Understanding The Semidefinite Relaxations of Truncated Least-Squares in Robust Rotation Search
To induce robustness against outliers for rotation search, prior work considers truncated least-squares (TLS), which is a non-convex optimization problem, and its semidefinite relaxation (SDR) as a tractable alternative.
Analysis and Extensions of Adversarial Training for Video Classification
Our first contribution is to show that generating optimal attacks for video requires carefully tuning the attack parameters, especially the step size.
ARCS: Accurate Rotation and Correspondence Search
We first propose a solver, $\texttt{ARCS}$, that i) assumes noiseless point sets in general position, ii) requires only $2$ inliers, iii) uses $O(m\log m)$ time and $O(m)$ space, and iv) can successfully solve the problem even with, e. g., $m, n\approx 10^6$ in about $0. 1$ seconds.
Reverse Engineering $\ell_p$ attacks: A block-sparse optimization approach with recovery guarantees
We pose this problem as a block-sparse recovery problem, where both the signal and the attack are assumed to lie in a union of subspaces that includes one subspace per class and one subspace per attack type.
Implicit Bias of Projected Subgradient Method Gives Provable Robust Recovery of Subspaces of Unknown Codimension
Robust subspace recovery (RSR) is a fundamental problem in robust representation learning.
Weakly-Supervised Generation and Grounding of Visual Descriptions With Conditional Generative Models
Given weak supervision from image- or video-caption pairs, we address the problem of grounding (localizing) each object word of a ground-truth or generated sentence describing a visual input.
Learning a Self-Expressive Network for Subspace Clustering
We show that our SENet can not only learn the self-expressive coefficients with desired properties on the training data, but also handle out-of-sample data.
Doubly Stochastic Subspace Clustering
Many state-of-the-art subspace clustering methods follow a two-step process by first constructing an affinity matrix between data points and then applying spectral clustering to this affinity.
Ranked #1 on
Image Clustering
on UMist
A Critique of Self-Expressive Deep Subspace Clustering
To extend this approach to data supported on a union of non-linear manifolds, numerous studies have proposed learning an embedding of the original data using a neural network which is regularized by a self-expressive loss function on the data in the embedded space to encourage a union of linear subspaces prior on the data in the embedded space.
A Game Theoretic Analysis of Additive Adversarial Attacks and Defenses
Research in adversarial learning follows a cat and mouse game between attackers and defenders where attacks are proposed, they are mitigated by new defenses, and subsequently new attacks are proposed that break earlier defenses, and so on.
On dissipative symplectic integration with applications to gradient-based optimization
More specifically, we show that a generalization of symplectic integrators to nonconservative and in particular dissipative Hamiltonian systems is able to preserve rates of convergence up to a controlled error.
Finding the Sparsest Vectors in a Subspace: Theory, Algorithms, and Applications
The problem of finding the sparsest vector (direction) in a low dimensional subspace can be considered as a homogeneous variant of the sparse recovery problem, which finds applications in robust subspace recovery, dictionary learning, sparse blind deconvolution, and many other problems in signal processing and machine learning.
A Linearly Convergent Method for Non-Smooth Non-Convex Optimization on the Grassmannian with Applications to Robust Subspace and Dictionary Learning
Minimizing a non-smooth function over the Grassmannian appears in many applications in machine learning.
On the Regularization Properties of Structured Dropout
We also show that the global minimizer for DropBlock can be computed in closed form, and that DropConnect is equivalent to Dropout.
The fastest $\ell_{1,\infty}$ prox in the west
In this paper we study the proximal operator of the mixed $\ell_{1,\infty}$ matrix norm and show that it can be computed in closed form by applying the well-known soft-thresholding operator to each column of the matrix.
Gradient flows and proximal splitting methods: A unified view on accelerated and stochastic optimization
We show that similar discretization schemes applied to Newton's equation with an additional dissipative force, which we refer to as accelerated gradient flow, allow us to obtain accelerated variants of all these proximal algorithms -- the majority of which are new although some recover known cases in the literature.
Representation Learning on Visual-Symbolic Graphs for Video Understanding
To capture this rich visual and semantic context, we propose using two graphs: (1) an attributed spatio-temporal visual graph whose nodes correspond to actors and objects and whose edges encode different types of interactions, and (2) a symbolic graph that models semantic relationships.
Ranked #10 on
Action Detection
on Charades
(using extra training data)
Conformal Symplectic and Relativistic Optimization
Arguably, the two most popular accelerated or momentum-based optimization methods in machine learning are Nesterov's accelerated gradient and Polyaks's heavy ball, both corresponding to different discretizations of a particular second order differential equation with friction.
On Geometric Analysis of Affine Sparse Subspace Clustering
In this paper, we develop a novel geometric analysis for a variant of SSC, named affine SSC (ASSC), for the problem of clustering data from a union of affine subspaces.
A Nonsmooth Dynamical Systems Perspective on Accelerated Extensions of ADMM
Recently, there has been great interest in connections between continuous-time dynamical systems and optimization methods, notably in the context of accelerated methods for smooth and unconstrained problems.
Monocular Object Orientation Estimation using Riemannian Regression and Classification Networks
We consider the task of estimating the 3D orientation of an object of known category given an image of the object and a bounding box around it.
Global Optimality in Separable Dictionary Learning with Applications to the Analysis of Diffusion MRI
In the classical setting, signals are represented as vectors and the dictionary learning problem is posed as a matrix factorization problem where the data matrix is approximately factorized into a dictionary matrix and a sparse matrix of coefficients.
End-to-End Fine-Grained Action Segmentation and Recognition Using Conditional Random Field Models and Discriminative Sparse Coding
We introduce an end-to-end algorithm for jointly learning the weights of the CRF model, which include action classification and action transition costs, as well as an overcomplete dictionary of mid-level action primitives.
Ranked #5 on
Action Segmentation
on JIGSAWS
An Analysis of Dropout for Matrix Factorization
While the resulting regularizer is closely related to a variational form of the nuclear norm, suggesting that dropout may limit the size of the factorization, we show that it is possible to trivially lower the objective value by doubling the size of the factorization.
(k,q)-Compressed Sensing for dMRI with Joint Spatial-Angular Sparsity Prior
Advanced diffusion magnetic resonance imaging (dMRI) techniques, like diffusion spectrum imaging (DSI) and high angular resolution diffusion imaging (HARDI), remain underutilized compared to diffusion tensor imaging because the scan times needed to produce accurate estimations of fiber orientation are significantly longer.
Provable Self-Representation Based Outlier Detection in a Union of Subspaces
While outlier detection methods based on robust statistics have existed for decades, only recently have methods based on sparse and low-rank representation been developed along with guarantees of correct outlier detection when the inliers lie in one or more low-dimensional subspaces.
Joint Spatial-Angular Sparse Coding for dMRI with Separable Dictionaries
High angular resolution diffusion imaging (HARDI) can produce better estimates of fiber orientation than the popularly used diffusion tensor imaging, but the high number of samples needed to estimate diffusivity requires longer patient scan times.
Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering Framework
In this paper, we propose a joint optimization framework --- Structured Sparse Subspace Clustering (S$^3$C) --- for learning both the affinity and the segmentation.
Car Segmentation and Pose Estimation using 3D Object Models
Image segmentation and 3D pose estimation are two key cogs in any algorithm for scene understanding.
Moving poselets: A discriminative and interpretable skeletal motion representation for action recognition
While automatic feature learning methods such as supervised sparse dictionary learning or neural networks can be applied to learn feature representation and action classifiers jointly, the resulting features are usually uninterpretable.
Finding Exemplars from Pairwise Dissimilarities via Simultaneous Sparse Recovery
Given pairwise dissimilarities between data points, we consider the problem of finding a subset of data points called representatives or exemplars that can efficiently describe the data collection.
Sparse Manifold Clustering and Embedding
We propose an algorithm called Sparse Manifold Clustering and Embedding (SMCE) for simultaneous clustering and dimensionality reduction of data lying in multiple nonlinear manifolds.
