AIConfPaper
← Search

Abdul Fatir Ansari

13 accepted papers

2026

Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting

Mert Kayaalp, Ali Caner Turkmen, Oleksandr Shchur, Pedro Mercado, Abdul Fatir Ansari, Michael Bohlke-Schneider +1
ICLR 2026poster

Is bigger always better for time series foundation models? With the question in mind, we explore an alternative to training a single, large monolithic model: building a portfolio of smaller, pretrained forecasting models. By applying ensembling or model selection over these portfolios, we achieve co…

Cited by 0Source ↗Scholar ↗
2026

Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility

Annan Yu, Danielle C. Maddix, Boran Han, Xiyuan Zhang, Abdul Fatir Ansari, Oleksandr Shchur +4
ICLR 2026poster

Transformers are widely used across data modalities, and yet the principles distilled from text models often transfer imperfectly. In this paper, we analyze Transformers through the lens of rank structure. Our focus is on the time series setting, where the structural properties of the data remarkabl…

Cited by 0Source ↗code ↗Scholar ↗
2026

Understanding the Implicit Biases of Design Choices for Time Series Foundation Models

Annan Yu, Danielle C. Maddix, Boran Han, Xiyuan Zhang, Abdul Fatir Ansari, Oleksandr Shchur +4
ICLR 2026poster

Time series foundation models (TSFMs) are a potential class of powerful, general-purpose tools for forecasting and related temporal tasks, but their behavior is strongly shaped by subtle inductive biases in their design. Rather than developing a new model and claiming that it is better than existin…

Cited by 0Source ↗Scholar ↗
2025

ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables

Sebastian Pineda Arango, Pedro Mercado, Shubham Kapoor, Abdul Fatir Ansari, Lorenzo Stella, Huibin Shen +7
AISTATS 2025poster

Covariates provide valuable information on external factors that influence time series and are critical in many real-world time series forecasting tasks. For example, in retail, covariates may indicate promotions or peak dates such as holiday seasons that heavily influence demand forecasts. Recent a…

Cited by 0Source ↗Scholar ↗
2025

Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization

Luca Masserano, Abdul Fatir Ansari, Boran Han, Xiyuan Zhang, Christos Faloutsos, Michael W. Mahoney +5
ICML 2025poster

How to best develop foundational models for time series forecasting remains an important open question. Tokenization is a crucial consideration in this effort: what is an effective discrete vocabulary for a real-valued sequential input? To address this question, we develop WaveToken, a wavelet-based…

Cited by 2Source ↗PDF ↗Scholar ↗
2025

Gradient-Free Generation for Hard-Constrained Systems

Chaoran Cheng, Boran Han, Danielle C. Maddix, Abdul Fatir Ansari, Andrew Stuart, Michael W. Mahoney +1
ICLR 2025poster

Generative models that satisfy hard constraints are critical in many scientific and engineering applications, where physical laws or system requirements must be strictly respected. Many existing constrained generative models, especially those developed for computer vision, rely heavily on gradient i…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models

Xiyuan Zhang, Danielle C. Maddix, Junming Yin, Nick Erickson, Abdul Fatir Ansari, Boran Han +8
NeurIPS 2025poster

Since the seminal work of TabPFN, research on tabular foundation models (TFMs) based on in-context learning (ICL) has challenged long-standing paradigms in machine learning. Without seeing any real-world data, models pretrained on purely synthetic datasets generalize remarkably well across diverse d…

Cited by 0Source ↗Scholar ↗
2023

Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series

Abdul Fatir Ansari, Alvin Heng, Andre Lim, Harold Soh
ICML 2023oral

Learning accurate predictive models of real-world dynamic phenomena (e.g., climate, biological) remains a challenging task. One key issue is that the data generated by both natural and artificial processes often comprise time series that are irregularly sampled and/or contain missing observations. I…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗
2023

Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting

Marcel Kollovieh, Abdul Fatir Ansari, Michael Bohlke-Schneider, Jasper Zschiegner, Hao Wang, Bernie Wang
NeurIPS 2023poster

Diffusion models have achieved state-of-the-art performance in generative modeling tasks across various domains. Prior works on time series diffusion models have primarily focused on developing conditional models tailored to specific forecasting or imputation tasks. In this work, we explore the pote…

Cited by 66Source ↗PDF ↗code ↗Scholar ↗
2021

Deep Explicit Duration Switching Models for Time Series

Abdul Fatir Ansari, Konstantinos Benidis, Richard Kurle, Ali Caner Turkmen, Harold Soh, Alex Smola +2
NeurIPS 2021poster

Many complex time series can be effectively subdivided into distinct regimes that exhibit persistent dynamics. Discovering the switching behavior and the statistical patterns in these regimes is important for understanding the underlying dynamical system. We propose the Recurrent Explicit Duration S…

Cited by 35Source ↗PDF ↗code ↗Scholar ↗
2021

Refining Deep Generative Models via Discriminator Gradient Flow

Abdul Fatir Ansari, Ming Liang Ang, Harold Soh
ICLR 2021poster

Deep generative modeling has seen impressive advances in recent years, to the point where it is now commonplace to see simulated samples (e.g., images) that closely resemble real-world data. However, generation quality is generally inconsistent for any given model and can vary dramatically between s…

Cited by 63Source ↗PDF ↗code ↗Scholar ↗
2020

A Characteristic Function Approach to Deep Implicit Generative Modeling

Abdul Fatir Ansari, Jonathan Scarlett, Harold Soh
CVPR 2020oral

Implicit Generative Models (IGMs) such as GANs have emerged as effective data-driven models for generating samples, particularly images. In this paper, we formulate the problem of learning an IGM as minimizing the expected distance between characteristic functions. Specifically, we minimize the dist…

Cited by 46PDF ↗code ↗Scholar ↗
2020

Event-Driven Visual-Tactile Sensing and Learning for Robots

Tasbolat Taunyazov, Weicong Sng, Brian Lim, Hian Hian See, Jethro Kuan, Abdul Fatir Ansari +2
RSS 2020poster

This work contributes an event-driven visual-tactile perception system, comprising a novel biologically-inspired tactile sensor and multi-modal spike-based learning. Our neuromorphic fingertip tactile sensor, NeuTouch, scales well with the number of taxels thanks to its event-based nature. Likewise,…

Cited by 125Source ↗PDF ↗Scholar ↗