194 citations · 649 across the 42 of their papers we have counts for
45 papers
Bootstrap-Conditioned Action Selection with Tabular Foundation Models
Devansh Gupta, Shiv Tavker, Dmitry Efimov +3
Contextual bandits offer a natural framework for sample-efficient personalization, but practical deployment remains difficult under sparse, biased interaction data, unreliable unce…
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…
Time-Aware Prior Fitted Networks for Zero-Shot Forecasting with Exogenous Variables
Andres Potapczynski, Ravi Kiran Selvam, Tatiana Konstantinova +7
In many time series forecasting settings, the target time series is accompanied by exogenous covariates, such as promotions and prices in retail demand; temperature in energy load;…
Zero-shot Forecasting by Simulation Alone
Boris N. Oreshkin, Mayank Jauhari, Ravi Kiran Selvam +10
Zero-shot time-series forecasting holds great promise, but is still in its infancy, hindered by limited and biased data corpora, leakage-prone evaluation, and privacy and licensing…
Efficiently Generating Correlated Sample Paths from Multi-step Time Series Foundation Models
Ethan Baron, Boris Oreshkin, Ruijun Ma +5
Many time series applications require access to multi-step forecast trajectories in the form of sample paths. Recently, time series foundation models have leveraged multi-step look…
Forking-Sequences: Statistically and Computationally Efficient Multi-Horizon Forecasting with Reduced Volatility
Willa Potosnak, Malcolm Wolff, Mengfei Cao +6
While accuracy is a critical requirement for time series forecasting, an equally important desideratum is reasonable forecast volatility across forecast creation dates (FCDs). Even…
A More Realistic Evaluation of Cross-Frequency Transfer Learning and Foundation Forecasting Models
Kin G. Olivares, Malcolm Wolff, Tatiana Konstantinova +8
Cross-frequency transfer learning (CFTL) has emerged as a popular framework for curating large-scale time series datasets to pre-train foundation forecasting models (FFMs). Althoug…
Probabilistic Pretraining for Neural Regression
Boris N. Oreshkin, Shiv Tavker, Dmitry Efimov
Transfer learning for probabilistic regression remains underexplored. This work closes this gap by introducing NIAQUE, Neural Interpretable Any-Quantile Estimation, a new model des…
TAT: Temporal-Aligned Transformer for Multi-Horizon Peak Demand Forecasting
Zhiyuan Zhao, Sitan Yang, Kin G. Olivares +5
Multi-horizon time series forecasting has many practical applications such as demand forecasting. Accurate demand prediction is critical to help make buying and inventory decisions…
SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting
Yitian Zhang, Liheng Ma, Antonios Valkanas +2
Koopman operator theory provides a framework for nonlinear dynamical system analysis and time-series forecasting by mapping dynamics to a space of real-valued measurement functions…
Quantile Regression with Large Language Models for Price Prediction
Nikhita Vedula, Dushyanta Dhyani, Laleh Jalali +3
Large Language Models (LLMs) have shown promise in structured prediction tasks, including regression, but existing approaches primarily focus on point estimates and lack systematic…
Enhanced N-BEATS for Mid-Term Electricity Demand Forecasting
Mateusz Kasprzyk, Paweł Pełka, Boris N. Oreshkin +1
This paper presents an enhanced N-BEATS model, N-BEATS*, for improved mid-term electricity load forecasting (MTLF). Building on the strengths of the original N-BEATS architecture,…
SPADE Split Peak Attention DEcomposition
Malcolm Wolff, Kin G. Olivares, Boris Oreshkin +8
Demand forecasting faces challenges induced by Peak Events (PEs) corresponding to special periods such as promotions and holidays. Peak events create significant spikes in demand f…
Dynamic layer selection in decoder-only transformers
Theodore Glavas, Joud Chataoui, Florence Regol +4
The vast size of Large Language Models (LLMs) has prompted a search to optimize inference. One effective approach is dynamic inference, which adapts the architecture to the sample-…
Online Posterior Sampling with a Diffusion Prior
Branislav Kveton, Boris Oreshkin, Youngsuk Park +2
Posterior sampling in contextual bandits with a Gaussian prior can be implemented exactly or approximately using the Laplace approximation. The Gaussian prior is computationally ef…
MODL: Multilearner Online Deep Learning
Antonios Valkanas, Boris N. Oreshkin, Mark Coates
Online deep learning tackles the challenge of learning from data streams by balancing two competing goals: fast learning and deep learning. However, existing research primarily emp…
Any-Quantile Probabilistic Forecasting of Short-Term Electricity Demand
Slawek Smyl, Boris N. Oreshkin, Paweł Pełka +1
Power systems operate under uncertainty originating from multiple factors that are impossible to account for deterministically. Distributional forecasting is used to control and mi…
3D Human Pose and Shape Estimation via HybrIK-Transformer
Boris N. Oreshkin
HybrIK relies on a combination of analytical inverse kinematics and deep learning to produce more accurate 3D pose estimation from 2D monocular images. HybrIK has three major compo…
SMPL-IK: Learned Morphology-Aware Inverse Kinematics for AI Driven Artistic Workflows
Vikram Voleti, Boris N. Oreshkin, Florent Bocquelet +3
Inverse Kinematics (IK) systems are often rigid with respect to their input character, thus requiring user intervention to be adapted to new skeletons. In this paper we aim at crea…
N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting
Cristian Challu, Kin G. Olivares, Boris N. Oreshkin +3
Recent progress in neural forecasting accelerated improvements in the performance of large-scale forecasting systems. Yet, long-horizon forecasting remains a very difficult task. T…
Motion Inbetweening via Deep -Interpolator
Boris N. Oreshkin, Antonios Valkanas, Félix G. Harvey +3
We show that the task of synthesizing human motion conditioned on a set of key frames can be solved more accurately and effectively if a deep learning based interpolator operates i…
Neural forecasting at scale
Philippe Chatigny, Shengrui Wang, Jean-Marc Patenaude +1
We study the problem of efficiently scaling ensemble-based deep neural networks for multi-step time series (TS) forecasting on a large set of time series. Current state-of-the-art…
ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics
Boris N. Oreshkin, Florent Bocquelet, Félix G. Harvey +2
Our work focuses on the development of a learnable neural representation of human pose for advanced AI assisted animation tooling. Specifically, we tackle the problem of constructi…
Adaptive filters for the moving target indicator system
Boris N. Oreshkin
Adaptive algorithms belong to an important class of algorithms used in radar target detection to overcome prior uncertainty of interference covariance. The contamination of the emp…