arXiv Machine Learning September 10, 2026 By Roberto Tacconelli

Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model

Read the original on arXiv Machine Learning →

The Flow has not summarised this story yet — read it at arXiv Machine Learning.

arXiv Machine Learning

Sep 18

When Does Retrieval Help Time-Series Forecasting?

arXiv:2609. 20193v1 Announce Type: new Abstract: Retrieval plug-ins supply a deep forecaster with information its lookback window cannot carry.

By Mert Onur Cakiroglu, Elham Buxton, Mehmet Dalkilic, Hasan Kurban

diffusion benchmarks

arXiv Machine Learning

Jul 7

When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters

arXiv:2607. 04919v1 Announce Type: new Abstract: Deploying a time series foundation model requires GPU infrastructure, engineering overhead, and carries no guarantee of improvement over XGBoost.

By Nicholas Tan Jerome, Frank Simon

llms fine-tuning benchmarks

arXiv Machine Learning

4d ago

Scaling Zero-Order Pretraining through Model Sharding

arXiv:2609.37899v1 Announce Type: new Abstract: Zero-order optimization (ZO) trains without backpropagation, making it relevant to forward-only hardware and non-differentiable loss, but its gradient...

By Francois Chaubard, Mykel J. Kochenderfer, Chris R\'e

arXiv Machine Learning

4d ago

CADENCE: A Confidence-Adaptive Dual-Expert Network for Fast and Accurate Time Series Classification

arXiv:2609.35929v1 Announce Type: new Abstract: Time series classification (TSC) exhibits a sharp trade-off between accuracy and computational scalability. Meta-ensembles like HIVE-COTE 2.0 reach sta...

By Onisa Mpaunda

benchmarks

arXiv Machine Learning

Jul 23

Trend strength predicts when generative foundation models win: a power-controlled benchmark, a mechanism, and an actionable selection rule

arXiv:2607. 19383v1 Announce Type: cross Abstract: Pretrained generative foundation models cast forecasting as conditional generation from a learned predictive distribution and forecast unseen series zero-shot.

By Ahmed Cherif

benchmarks

arXiv Machine Learning

Aug 4

Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors

arXiv:2608. 00675v1 Announce Type: cross Abstract: Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it against.

By Alexander Scheinker

diffusion benchmarks

One email a morning, machine-written

Related stories

When Does Retrieval Help Time-Series Forecasting?

When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters

Scaling Zero-Order Pretraining through Model Sharding

CADENCE: A Confidence-Adaptive Dual-Expert Network for Fast and Accurate Time Series Classification

Trend strength predicts when generative foundation models win: a power-controlled benchmark, a mechanism, and an actionable selection rule

Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors