Search Results for author:
Found 16 papers, 6 papers with code
How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse
With the aim of rigorously understanding model collapse in language models, we consider in this paper a statistical model that allows us to characterize the impact of various recursive training scenarios.
Performance Gaps in Multi-view Clustering under the Nested Matrix-Tensor Model
We study the estimation of a planted signal hidden in a recently introduced nested matrix-tensor model, which is an extension of the classical spiked rank-one tensor model, motivated by multi-view clustering.
Do Vision and Language Encoders Represent the World Similarly?
In the absence of statistical similarity in aligned encoders like CLIP, we show that a possible matching of unaligned encoders exists without any training.
On the Accuracy of Hotelling-Type Asymmetric Tensor Deflation: A Random Tensor Analysis
This work introduces an asymptotic study of Hotelling-type tensor deflation in the presence of noise, in the regime of large tensor dimensions.
A Nested Matrix-Tensor Model for Noisy Multi-view Clustering
In order to study the theoretical performance of this approach, we characterize the behavior of this best rank-one approximation in terms of the alignments of the obtained component vectors with the hidden model parameter vectors, in the large-dimensional regime.
Hotelling Deflation on Large Symmetric Spiked Tensors
This paper studies the deflation algorithm when applied to estimate a low-rank symmetric spike contained in a large tensor corrupted by additive Gaussian noise.
Optimizing Orthogonalized Tensor Deflation via Random Tensor Theory
Relying on recently developed random tensor tools, this paper deals precisely with the non-orthogonal case by deriving an asymptotic analysis of a parameterized deflation procedure performed on an order-three and rank-two spiked tensor.
On the Accuracy of Hotelling-Type Tensor Deflation: A Random Tensor Analysis
Leveraging on recent advances in random tensor theory, we consider in this paper a rank-$r$ asymmetric spiked tensor model of the form $\sum_{i=1}^r \beta_i A_i + W$ where $\beta_i\geq 0$ and the $A_i$'s are rank-one tensors such that $\langle A_i, A_j \rangle\in [0, 1]$ for $i\neq j$, based on which we provide an asymptotic study of Hotelling-type tensor deflation in the large dimensional regime.
When Random Tensors meet Random Matrices
Relying on random matrix theory (RMT), this paper studies asymmetric order-$d$ spiked tensor models with Gaussian noise.
Node Feature Kernels Increase Graph Convolutional Network Robustness
The robustness of the much-used Graph Convolutional Networks (GCNs) to perturbations of their input is becoming a topic of increasing importance.
Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification
These networks, although effective in multiple tasks such as classification or object detection, tend to focus on the most discriminative part of an object rather than retrieving all its relevant features.
Ranked #4 on
Person Re-Identification
on CUHK03 detected
Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures
This paper shows that deep learning (DL) representations of data produced by generative adversarial nets (GANs) are random vectors which fall within the class of so-called \textit{concentrated} random vectors.
A Kernel Random Matrix-Based Approach for Sparse PCA
In this paper, we present a random matrix approach to recover sparse principal components from n p-dimensional vectors.
Deep Multi-class Adversarial Specularity Removal
We propose a novel learning approach, in the form of a fully-convolutional neural network (CNN), which automatically and consistently removes specular highlights from a single image by generating its diffuse component.
Generative Collaborative Networks for Single Image Super-Resolution
In this paper, we present a general framework named \textit{Generative Collaborative Networks} (GCN), where the idea consists in optimizing the \textit{generator} (the mapping of interest) in the feature space of a \textit{features extractor} network.
Learning More Universal Representations for Transfer-Learning
We also propose a unified framework of the methods based on the diversifying of the training problem.
