Search Results for author:
Found 55 papers, 8 papers with code
Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization
To address this misalignment, we propose a spectral initialization for LoRA in MF and theoretically prove that GF with small spectral initialization converges to the fine-tuning task with arbitrary precision.
Disentangling Safe and Unsafe Corruptions via Anisotropy and Locality
The proposed threat model measures the threat of a perturbation via its alignment with \textit{unsafe directions}, defined as directions in the input space along which a perturbation of sufficient magnitude changes the ground truth class label.
Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery
In this setting, we provide, for the first time in the literature, linear convergence guarantees for the derived overparameterized preconditioned subgradient algorithm in the presence of gross corruptions.
Recommendation with Generative Models
Generative models are a class of AI models capable of creating new instances of data by learning and sampling from their statistical distributions.
Multi-modal Generative Models in Recommendation System
Many recommendation systems limit user inputs to text strings or behavior signals such as clicks and purchases, and system outputs to a list of products sorted by relevance.
Large Language Model Driven Recommendation
While previous chapters focused on recommendation systems (RSs) based on standardized, non-verbal user feedback such as purchases, views, and clicks -- the advent of LLMs has unlocked the use of natural language (NL) interactions for recommendation.
Semantic-aware Video Representation for Few-shot Action Recognition
In this work, we propose a simple yet effective Semantic-Aware Few-Shot Action Recognition (SAFSAR) model to address these issues.
Clustering-based Domain-Incremental Learning
A key challenge in this setting is the so-called "catastrophic forgetting problem", in which the performance of the learner in an "old task" decreases when subsequently trained on a "new task".
Variational Information Pursuit with Large Language and Multimodal Models for Interpretable Predictions
Variational Information Pursuit (V-IP) is a framework for making interpretable predictions by design by sequentially selecting a short chain of task-relevant, user-defined and interpretable queries about the data that are most informative for the task.
Efficient Vision Transformer for Human Pose Estimation via Patch Selection
While Convolutional Neural Networks (CNNs) have been widely successful in 2D human pose estimation, Vision Transformers (ViTs) have emerged as a promising alternative to CNNs, boosting state-of-the-art performance.
Learning Globally Smooth Functions on Manifolds
To do so, it shows that under typical conditions the problem of learning a Lipschitz continuous function on a manifold is equivalent to a dynamically weighted manifold regularization problem.
Interpretable by Design: Learning Predictors by Composing Interpretable Queries
There is a growing concern about typically opaque decision-making with high-performance machine learning algorithms.
The Vision of Self-Evolving Computing Systems
We motivate the need for self-evolving computing systems in light of the state of the art, outline a conceptual architecture of self-evolving computing systems, and illustrate the architecture for a future smart city mobility system that needs to evolve continuously with changing conditions.
Structured Graph Variational Autoencoders for Indoor Furniture layout Generation
The architecture consists of a graph encoder that maps the input graph to a structured latent space, and a graph decoder that generates a furniture graph, given a latent code and the room graph.
Boosting RANSAC via Dual Principal Component Pursuit
In this paper, we revisit the problem of local optimization in RANSAC.
Attention: Self-Expression Is All You Need
Much of their success is attributed to the use of attention layers that capture long-range interactions among data tokens (such as words and image patches) via attention coefficients that are global and adapted to the input data at test time.
Implicit Bias of Projected Subgradient Method Gives Provable Robust Recovery of Subspaces of Unknown Codimension
In particular, we show that 1) all of the problem instances will converge to a vector in the null space of the subspace and 2) the ensemble of problem instance solutions will be sufficiently diverse to fully span the null space of the subspace (and thus reveal the true codimension of the subspace) even when the true subspace dimension is unknown.
Convergence and Implicit Bias of Gradient Flow on Overparametrized Linear Networks
Firstly, we show that the squared loss converges exponentially to its optimum at a rate that depends on the level of imbalance and the margin of the initialization.
Implicit Acceleration of Gradient Flow in Overparameterized Linear Models
More precisely, gradient flow preserves the difference of the Gramian~matrices of the input and output weights and we show that the amount of acceleration depends on both the magnitude of that difference (which is fixed at initialization) and the spectrum of the data.
Quantifying Task Complexity Through Generalized Information Measures
In this paper, we propose to measure the complexity of a learning task by the minimum expected number of questions that need to be answered to solve the task.
On the Explicit Role of Initialization on the Convergence and Generalization Properties of Overparametrized Linear Networks
In this paper, we present a novel analysis of overparametrized single-hidden layer linear networks, which formally connects initialization, optimization, and overparametrization with generalization performance.
Self-Representation Based Unsupervised Exemplar Selection in a Union of Subspaces
When the dataset is drawn from a union of independent subspaces, our method is able to select sufficiently many representatives from each subspace.
Is an Affine Constraint Needed for Affine Subspace Clustering?
Specifically, our analysis provides conditions that guarantee the correctness of affine subspace clustering methods both with and without the affine constraint, and shows that these conditions are satisfied for high-dimensional data.
Basis Pursuit and Orthogonal Matching Pursuit for Subspace-preserving Recovery: Theoretical Analysis
The goal is to have the representation $c$ correctly identify the subspace, i. e. the nonzero entries of $c$ should correspond to columns of $A$ that are in the subspace $\mathcal{S}_0$.
What is the Largest Sparsity Pattern that Can Be Recovered by 1-Norm Minimization?
In the case of the partial discrete Fourier transform, our characterization of the largest sparsity pattern that can be recovered requires the unknown signal to be real and its dimension to be a prime number.
Dual Principal Component Pursuit: Probability Analysis and Efficient Algorithms
However, its geometric analysis is based on quantities that are difficult to interpret and are not amenable to statistical analysis.
Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms
However, its geometric analysis is based on quantities that are difficult to interpret and are not amenable to statistical analysis.
Nonconvex Robust Low-rank Matrix Recovery
In this paper we study the problem of recovering a low-rank matrix from a number of random linear measurements that are corrupted by outliers taking arbitrary values.
Information Theory Information Theory
Scalable Exemplar-based Subspace Clustering on Class-Imbalanced Data
Our experiments demonstrate that the proposed method outperforms state-of-the-art subspace clustering methods in two large-scale image datasets that are imbalanced.
ADMM and Accelerated ADMM as Continuous Dynamical Systems
Recently, there has been an increasing interest in using tools from dynamical systems to analyze the behavior of simple optimization algorithms such as gradient descent and accelerated variants.
On the Implicit Bias of Dropout
Algorithmic approaches endow deep learning systems with implicit bias that helps them generalize even in over-parametrized settings.
A Mixed Classification-Regression Framework for 3D Pose Estimation from 2D Images
Since 3D pose is a continuous quantity, a natural formulation for this task is to solve a pose regression problem.
Theoretical Analysis of Sparse Subspace Clustering with Missing Entries
The main insight that stems from our analysis is that even though the projection induces additional missing entries, this is counterbalanced by the fact that the projected and zero-filled data are in effect incomplete points associated with the union of the corresponding projected subspaces, with respect to which the point being expressed is complete.
Mathematics of Deep Learning
Recently there has been a dramatic increase in the performance of recognition systems due to the introduction of deep architectures for representation learning and classification.
Stretching Domain Adaptation: How far is too far?
This work pushes the limit of unsupervised domain adaptation through an in-depth evaluation of several state of the art methods on benchmark datasets and the new dataset suite.
Convolutional Networks for Object Category and 3D Pose Estimation from 2D Images
In this paper, we relax one of these constraints and propose to solve the task of joint object category and 3D pose estimation from an image assuming known 2D localization.
Dropout as a Low-Rank Regularizer for Matrix Factorization
Regularization for matrix factorization (MF) and approximation problems has been carried out in many different ways.
Structured Low-Rank Matrix Factorization: Global Optimality, Algorithms, and Applications
Recently, convex formulations of low-rank matrix factorization problems have received considerable attention in machine learning.
3D Pose Regression using Convolutional Neural Networks
3D pose estimation is a key component of many important computer vision tasks such as autonomous navigation and 3D scene understanding.
Global Optimality in Neural Network Training
The past few years have seen a dramatic increase in the performance of recognition systems thanks to the introduction of deep networks for representation learning.
Hyperplane Clustering Via Dual Principal Component Pursuit
A thorough experimental evaluation reveals that hyperplane learning schemes based on DPCP dramatically improve over the state-of-the-art methods for the case of synthetic data, while are competitive to the state-of-the-art in the case of 3D plane clustering for Kinect data.
Curriculum Dropout
This induces an adaptive regularization scheme that smoothly increases the difficulty of the optimization problem.
Information Pursuit: A Bayesian Framework for Sequential Scene Parsing
Despite enormous progress in object detection and classification, the problem of incorporating expected contextual relationships among object instances into modern recognition systems remains a key challenge.
Temporal Convolutional Networks for Action Segmentation and Detection
The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond.
Temporal Convolutional Networks: A Unified Approach to Action Segmentation
The dominant paradigm for video-based action segmentation is composed of two steps: first, for each frame, compute low-level features using Dense Trajectories or a Convolutional Neural Network that encode spatiotemporal information locally, and second, input these features into a classifier that captures high-level temporal relationships, such as a Recurrent Neural Network (RNN).
Ranked #6 on
Action Segmentation
on JIGSAWS
Oracle Based Active Set Algorithm for Scalable Elastic Net Subspace Clustering
Our geometric analysis also provides a theoretical justification and a geometric interpretation for the balance between the connectedness (due to $\ell_2$ regularization) and subspace-preserving (due to $\ell_1$ regularization) properties for elastic net subspace clustering.
Ranked #7 on
Image Clustering
on coil-100
(Accuracy metric)
Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation
We propose a model for action segmentation which combines low-level spatiotemporal features with a high-level segmental classifier.
Ranked #7 on
Action Segmentation
on JIGSAWS
Filtrated Spectral Algebraic Subspace Clustering
Algebraic Subspace Clustering (ASC) is a simple and elegant method based on polynomial fitting and differentiation for clustering noiseless data drawn from an arbitrary union of subspaces.
Dual Principal Component Pursuit
We consider the problem of learning a linear subspace from data corrupted by outliers.
Algebraic Clustering of Affine Subspaces
Using notions from algebraic geometry, we prove that the homogenization trick, which embeds points in a union of affine subspaces into points in a union of linear subspaces, preserves the general position of the points and the transversality of the union of subspaces in the embedded space, thus establishing the correctness of ASC for affine subpaces.
Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit
Subspace clustering methods based on $\ell_1$, $\ell_2$ or nuclear norm regularization have become very popular due to their simplicity, theoretical guarantees and empirical success.
Ranked #6 on
Image Clustering
on Extended Yale-B
Global Optimality in Tensor Factorization, Deep Learning, and Beyond
Techniques involving factorization are found in a wide range of applications and have enjoyed significant empirical success in many fields.
Filtrated Algebraic Subspace Clustering
In the abstract form of the problem, where no noise or other corruptions are present, the data are assumed to lie in general position inside the algebraic variety of a union of subspaces, and the objective is to decompose the variety into its constituent subspaces.
Structured Sparse Subspace Clustering: A Unified Optimization Framework
Our framework is based on expressing each data point as a structured sparse linear combination of all other data points, where the structure is induced by a norm that depends on the unknown segmentation.
Sparse Subspace Clustering: Algorithm, Theory, and Applications
In this paper, we propose and study an algorithm, called Sparse Subspace Clustering (SSC), to cluster data points that lie in a union of low-dimensional subspaces.
Ranked #4 on
Motion Segmentation
on Hopkins155
