Arjun Ashok

Arjun Ashok

I am a Visiting Researcher (Full-Time) at ServiceNow Research, Montreal, Canada and a PhD student at MILA-Quebec AI Institute and Université de Montréal advised by Irina Rish and Alexandre Drouin. My research interests are in time series forecasting.

My email address is arjun.ashok [at] servicenow [dot] com. Email me if you'd like to connect, be it about research or music or anything else!



Descriptive Alt Text

News

Nov '24 Gave an oral presentation on Context is Key at the Workshop on Foundation Models for Time Series: Exploring New Frontiers co-located with ACM ICAIF 2024, New York, USA.
Oct '24 Paper on natural-language based context-aware forecasting, Context is Key: A Benchmark for Forecasting with Essential Textual Information, is out on arXiv.
Sep '24 Co-organizing the The first NeurIPS workshop on Time Series in the Age of Large Models at NeurIPS 2024 in December. Consider participating!
July '24 Gave an invited talk on Natural Language based Context-Aware Forecasting at the International Symposium on Forecasting (ISF) 2024.
May '24 Presented TACTiS-2 at ICLR 2024. TACTiS-2 is a highly flexible model for multivariate probabilistic time series prediction tasks. Check out the tweet thread and poster here!
Feb '24 The full version of Lag-Llama released with open-source model checkpoints! Check the announcement here!
Jan '24 I gave a talk on our efforts Towards General-Purpose Models for Time-Series Prediction at the Winter 2024 Montreal Time Series Meetup.
Jan '24 TACTiS-2 accepted at ICLR 2024!
Dec '23 I gave a talk on Building Foundation Models for Time Series Data at the 6th workshop on Neural Scaling Laws co-located with NeurIPS 2023.
Oct '23 TACTiS-2 is out on arXiv.
Oct '23 A preliminary version of Lag-Llama is out on arXiv.
Jan '23 One paper on out-of-distribution detection accepted to ICLR 2023. This is work in collaboration with folks at ML Collective mentored by Rosanne Liu.
Jan '23 Started as a Visiting Researcher (Full-Time) at ServiceNow Research, Montreal. Excited to continue working on problems in time series representation learning!
Aug '22 Preliminary work on self-supervised learning objectives for weather time series accepted at the AAAI 2022 Fall Symposium on Climate Change.
Jul '22 One paper on Class-Incremental Learning accepted as a full paper at ECCV 2022.
Jun '22 Started as a Research Intern at IBM Research, India. I'll be working on building self-supervised learning objectives and pre-trained models for geospatial weather time series.
Jun '22 One paper on cross-task generalization in NLP submitted to EMNLP 2022 (Update: Accepted).
Apr '22 One paper on Class-Incremental Learning accepted at the CLVISION Workshop at CVPR 2022 as a non-archival paper (Update: Accepted at ECCV 2022).
Apr '22 One reproducibility report on Self-Supervision and Few-shot Learning accepted at the ML Reproducibility Challenge 2021 (Fall Edition) and published at ReScience-C.
Oct '21 One paper on out-of-distribution generalization accepted as AAAI 2022 as a student abstract.
Jun '21 Started as a Research Assistant at IIT Hyderabad under Prof. Vineeth Balasubramanian.

Latest Papers

Context is Key: A Benchmark for Forecasting with Essential Textual Information
Arjun Ashok*, Andrew Robert Williams*, Étienne Marcotte, Valentina Zantedeschi, Jithendaraa Subramanian, Roland Riachi, James Requeima, Alexandre Lacoste, Irina Rish, Nicolas Chapados, Alexandre Drouin
(* Co-first authorship)
Preprint.
Accepted for Poster Presentation at NeurIPS 2024 Workshop on Time Series in the Age of Large Models
Accepted for Oral Presentation at ACM ICAIF 2024 Workshop on Foundation Models for Time Series: Exploring New Frontiers
Accepted for Poster Presentation at Montreal AI Symposium 2024

arXiv Code Benchmark Visualization Tweet

A forecasting benchmark with problems that require the combined use of numerical historical data and textual context.
Forecasting is a critical task in decision making across various domains. While numerical data provides a foundation, it often lacks crucial context necessary for accurate predictions. Human forecasters frequently rely on additional information, such as background knowledge or constraints, which can be efficiently communicated through natural language. However, the ability of existing forecasting models to effectively integrate this textual information remains an open question. To address this, we introduce "Context is Key" (CiK), a time series forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context, requiring models to integrate both modalities. We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters, and propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark. Our experiments highlight the importance of incorporating contextual information, demonstrate surprising performance when using LLM-based forecasting models, and also reveal some of their critical shortcomings. By presenting this benchmark, we aim to advance multimodal forecasting, promoting models that are both accurate and accessible to decision-makers with varied technical expertise. The benchmark can be visualized at https://servicenow.github.io/context-is-key-forecasting/.
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series
Arjun Ashok, Étienne Marcotte, Valentina Zantedeschi, Nicolas Chapados, Alexandre Drouin
Published at ICLR 2024
Also accepted for Oral Presentation at Montreal AI Symposium 2024

arXiv Code OpenReview Tweet Poster Blog 15-min Video

A flexible model for multivariate probabilistic time series prediction, simplifying the training of attentional copulas, with state-of-the-art accuracy on diverse forecasting tasks, while supporting interpolation and learning from irregular data.
We introduce a new model for multivariate probabilistic time series prediction, designed to flexibly address a range of tasks including forecasting, interpolation, and their combinations. Building on copula theory, we propose a simplified objective for the recently-introduced transformer-based attentional copulas (TACTiS), wherein the number of distributional parameters now scales linearly with the number of variables instead of factorially. The new objective requires the introduction of a training curriculum, which goes hand-in-hand with necessary changes to the original architecture. We show that the resulting model has significantly better training dynamics and achieves state-of-the-art performance across diverse real-world forecasting tasks, while maintaining the flexibility of prior work, such as seamless handling of unaligned and unevenly-sampled time series.
Lag-Llama: Towards Foundation Models for Time Series Forecasting
Arjun Ashok*, Kashif Rasul*, Andrew Robert Williams, Hena Ghonia, Rishika Bhagwatkar, Arian Khorasani, Mohammad Javad Darvishi Bayazi, George Adamopoulos, Roland Riachi, Nadhir Hassen, Marin Biloš, Sahil Garg, Anderson Schneider, Nicolas Chapados, Alexandre Drouin, Valentina Zantedeschi, Yuriy Nevmyvaka, Irina Rish
(* Co-first authorship)
Preprint.
Accepted for Poster Presentation at NeurIPS 2023 Workshop on Robustness of Few-shot and Zero-shot Learning in Foundation Models

Paper Code (1k+ ★) Weights Demo Tweet 15-min Video

A foundation model for probabilistic time series forecasting with strong zero-shot and few-shot capabilities
Over the past years, foundation models have caused a paradigm shift in machine learning due to their unprecedented capabilities for zero-shot and few-shot generalization. However, despite the success of foundation models in modalities such as natural language processing and computer vision, the development of foundation models for time series forecasting has lagged behind. We present Lag-Llama, a general-purpose foundation model for univariate probabilistic time series forecasting based on a decoder-only transformer architecture that uses lags as covariates. Lag-Llama is pretrained on a large corpus of diverse time series data from several domains, and demonstrates strong zero-shot generalization capabilities compared to a wide range of forecasting models on downstream datasets across domains. Moreover, when fine-tuned on relatively small fractions of such previously unseen datasets, Lag-Llama achieves state-of-the-art performance, outperforming prior deep learning approaches, emerging as the best general-purpose model on average. Lag-Llama serves as a strong contender to the current state-of-art in time series forecasting and paves the way for future advancements in foundation models tailored to time series data.

Previous Work

I previously worked on problems in out-of-distribution generalization, continual learning, and few-shot learning, spanning the domains of computer vision and natural language processing. Please check my Google Scholar for a list of previous publications.

Music

I am a Carnatic Vocalist and a student of Vidwan Bharat Sundar. I have performed Carnatic concerts in multiple venues in India, and continue to perform in and around Montréal and Ottawa regularly. Here is a recording of a concert of mine from July 2024.
From a concert performed in May 2022

Invited Talks

Academic Service