Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
The Theory behinds Denoising Diffusion Probabilistic Models
Published in Open Science, 2024
This paper contains the whole theory behinds Denoising Diffusion Probabilistic Models. The code is available in my github repo
The Theory behinds Variational Auto-Encoders
Published in Open Science, 2024
This paper contains the whole theory behinds Variational Auto-Encoders with some experiments. The code is available in my github repo.
Understanding Neural Tangent Kernel: Key Theories and Experimental Insights
Published in HAL Open Science, 2024
This paper is about fixing template issue #693.
A control of the false anomaly rate for Anomaly Detections problems on Images
Published in Open Science, 2024
This paper summarizes the initial stages of my thesis research. We focus in a first step on anomaly detection algorithms for image data. I explore various techniques and incorporate a thresholding procedure utilizing p-values, inspired by the work presented in Testing for Outliers with Conformal p-values. The code can be found here: github repo
Does Normalization Choice Matter for Causal Large Time-Series Models?
Published in ICLR 2026 TSALM Workshop, 2025
Large models for time-series forecasting have been emerged as a promisingparadigm for training models on heterogeneous collections of signals. These models typically rely on causal autoregressive architectures, where each observation is sequentially predicted from past. In practice, real-world time-series exhibit non-stationarities, which significantly influence predictive performance. To mitigate this, normalization is commonly employed However, in efficient causal settings it might induce information leakage from future observations during training. Recent alternatives, including causal normalization and statistics computed from initial observations, have been proposed to address this issue, but their practical implications remain insufficiently understood. In this work, we evaluate normalization strategies for transformer-based large time-series models trained with patching and efficient causal strategy. We showcase that normalization choice significantly influences both training convergence and forecasting performance.
PatchTrAD: A Patch-Based Transformer focusing on Patch-Wise Reconstruction Error for Time Series Anomaly Detection
Published in EUSIPCO 2025, 2025
Time series anomaly detection (TSAD) focuses on identifying whether observations in streaming data deviate significantly from normal patterns. With the prevalence of connected devices, anomaly detection on time series has become paramount, as it enables real-time monitoring and early detection of irregular behaviors across various application domains. In this work, we introduce PatchTrAD, a Patch-based Transformer model for time series anomaly detection. Our approach leverages a Transformer encoder along with the use of patches under a reconstructionbased framework for anomaly detection. Empirical evaluations on multiple benchmark datasets show that PatchTrAD is on par, in terms of detection performance, with state-of-the-art deep learning models for anomaly detection while being time efficient during inference. Github Repo
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.