4 citations · 10 across the 21 of their papers we have counts for
27 papers
A Large-Dimensional Analysis of Least-Squares Federated Learning via Generalized Total Variation Minimization
Ekkehard Schnoor, Malik Tiomoko, Alexander Jung
Federated learning over decentralized networks inherently trades off the suppression of local finite-sample noise through collaboration against the bias that collaboration introduc…
Instance-Adaptive Prompts as Context for Time-Series Foundation Models
Zehao Xiao, Shifeng Xie, Lei Zan +5
Longer histories can improve time-series foundation models (TSFMs), but require substantially higher inference cost. We therefore ask whether contextual information can be provided…
LLM-Generated Feature Pools for Time Series Anomaly Detection
Youssef Attia El Hili, Malik Tiomoko, Corinne Ancourt
We study how far a simple statistical pipeline can go on univariate time series anomaly detection under a strict selection protocol. The method extracts a small pool of statistics…
Tabby: An Open Pretraining Recipe for Time Series Foundation Models
Shifeng Xie, Bahaeddine Abdessalem, Zehao Xiao +9
In this report, we release Tabby, a long context probabilistic time series foundation model, together with a complete and open recipe of how it was built. Tabby adopts an encoder-o…
FlowTSFM: Turning Encoder Depth into Quantile Transport
Bahaeddine Abdessalem, Shifeng Xie, Zehao Xiao +6
Encoder-based time series foundation models (TSFMs) typically rely on deep stacks of independently parameterized Transformer layers, where only the final forecast is supervised and…
EvoCause: LLM-Guided Evolution of Causal Graphs for Root Cause Analysis
Lei Zan, Keli Zhang, Shifeng Xie +7
Modern telecommunication, cloud, and microservice systems emit correlated alarm cascades when components fail. Root cause analysis (RCA) aims to identify the small set of alarms th…
Post-Training in Time Series Foundation Models: A Unifying Framework
Shifeng Xie, Ambroise Odonnat, Zehao Xiao +7
Time series foundation models (TSFMs) have emerged as general-purpose models for time series analysis, but pretraining alone is often insufficient for reliable downstream deploymen…
-TCAV: A Unified Framework for Testing with Concept Activation Vectors
Ekkehard Schnoor, Jawher Said, Malik Tiomoko +2
Concept Activation Vectors (CAV) and the Testing with CAVs (TCAV) method are fundamental tools for concept-based explainability in deep learning, yet their practical utility is lim…
Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization
Chiheb Yaakoubi, Cosme Louart, Malik Tiomoko +1
We study high-dimensional convex empirical risk minimization (ERM) under general non-Gaussian data designs. By heuristically extending the Convex Gaussian Min-Max Theorem (CGMT) to…
Generalization in Representation Models via Random Matrix Theory: Application to Recurrent Networks
Yessin Moakher, Malik Tiomoko, Cosme Louart +1
We first study the generalization error of models that use a fixed feature representation (frozen intermediate layers) followed by a trainable readout layer. This setting encompass…
LLMs as In-Context Meta-Learners for Model and Hyperparameter Selection
Youssef Attia El Hili, Albert Thomas, Malik Tiomoko +4
Model and hyperparameter selection are critical but challenging in machine learning, typically requiring expert intuition or expensive automated search. We investigate whether larg…
A Random Matrix Perspective of Echo State Networks: From Precise Bias--Variance Characterization to Optimal Regularization
Yessin Moakher, Malik Tiomoko, Cosme Louart +1
We present a rigorous asymptotic analysis of Echo State Networks (ESNs) in a teacher student setting with a linear teacher with oracle weights. Leveraging random matrix theory, we…
Concept activation vectors: a unifying view and adversarial attacks
Ekkehard Schnoor, Malik Tiomoko, Jawher Said +2
Concept Activation Vectors (CAVs) are a tool from explainable AI, offering a promising approach for understanding how human-understandable concepts are encoded in a model's latent…
Incorporating priors in learning: a random matrix study under a teacher-student framework
Malik Tiomoko, Ekkehard Schnoor
Regularized linear regression is central to machine learning, yet its high-dimensional behavior with informative priors remains poorly understood. We provide the first exact asympt…
Breaking the Barriers of Text-Hungry and Audio-Deficient AI
Hamidou Tembine, Issa Bamia, Massa NDong +31
While global linguistic diversity spans more than 7164 recognized languages, the current dominant architecture of machine intelligence remains fundamentally biased toward written t…
Post-Training Corrections for Improved Time-Series Forecasting
Hamza Cherkaoui, Malik Tiomoko, Giuseppe Paolo +4
Time-series forecasting is a critical task in various business domains, but it remains inherently challenging. Typically, large forecasting models are trained in a single, resource…
High-Dimensional Analysis of Bootstrap Ensemble Classifiers
Malik Tiomoko, Hamza Cherkaoui, Mohamed El Amine Seddik +3
Bootstrap methods have long been the cornerstone of ensemble learning in machine learning. This paper presents a theoretical analysis of bootstrap techniques applied to the Least S…
Mantis: Lightweight Foundation Model for Time Series Classification
Vasilii Feofanov, Songkang Wen, Shifeng Xie +10
While foundation models have revolutionized various domains, their application to time series classification remains rather under-explored, with existing literature predominantly f…
User-friendly Foundation Model Adapters for Multivariate Time Series Classification
Vasilii Feofanov, Romain Ilbert, Malik Tiomoko +2
Foundation models, while highly effective, are often resource-intensive, requiring substantial inference time and memory. This paper addresses the challenge of making these models…
Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
Romain Ilbert, Malik Tiomoko, Cosme Louart +4
In this paper, we introduce a novel theoretical framework for multi-task regression, applying random matrix theory to provide precise performance estimations, under high-dimensiona…
Random matrix theory improved Fréchet mean of symmetric positive definite matrices
Florent Bouchard, Ammar Mian, Malik Tiomoko +2
In this study, we consider the realm of covariance matrices in machine learning, particularly focusing on computing Fréchet means on the manifold of symmetric positive definite mat…
Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption
Vasilii Feofanov, Malik Tiomoko, Aladin Virmaux
We propose a theoretical framework to analyze semi-supervised classification under the low density separation assumption in a high-dimensional regime. In particular, we introduce Q…
PCA-based Multi Task Learning: a Random Matrix Approach
Malik Tiomoko, Romain Couillet, Frédéric Pascal
The article proposes and theoretically analyses a \emph{computationally efficient} multi-task learning (MTL) extension of popular principal component analysis (PCA)-based supervise…
Multi-task learning on the edge: cost-efficiency and theoretical optimality
Sami Fakhry, Romain Couillet, Malik Tiomoko
This article proposes a distributed multi-task learning (MTL) algorithm based on supervised principal component analysis (SPCA) which is: (i) theoretically optimal for Gaussian mix…