AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution Drift
Accurate workload forecasting is critical for elastic resource provisioning in web-scale cloud services, where distribution shifts driven by viral content, product launches, and user behavior degrade offline-trained models rapidly.
Key points
- Naive online learning recovers accuracy but incurs prohibitive per-step compute cost.
- We propose AdaptLSTM, an adaptive online framework that detects drift via validation-calibrated thresholds and applies selective, targeted updates.
- On the Alibaba Machine Trace, AdaptLSTM recovers 54% of Naive Online's improvement at 20% cost ($2.7\times$ efficiency, $p=0.002$ over 10 seeds).
- Wall-clock profiling shows $1.33\times$ throughput gain and 45% update-time reduction.
Sources (1)
- [1]AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution DriftarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 04:31 PM
Accurate workload forecasting is critical for elastic resource provisioning in web-scale cloud services, where distribution shifts driven by viral content, product launches, and user behavior degrade offline-trained models rapidly.
Naive online learning recovers accuracy but incurs prohibitive per-step compute cost.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026ConwayResearch/Underdog-Saluki-27B-1.0
- Oct 8, 2026LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
- Oct 8, 2026One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
- Oct 8, 2026Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals
- Oct 7, 2026Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
- Oct 6, 2026EmbeddingGemma 2: an open, lightweight multimodal embedding model