Research map / Learning theory and algorithms / Matrix and tensor methods
Matrix Factorisation for Scalable Energy Breakdown
Nipun Batra, Hongning Wang, Amarjeet Singh, Kamin Whitehouse
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use matrix factorisation vs Gemello kNN-style matching | feature-based NMF · 105 homes, dish washer | RMS error in PEC: 1.05 -> 0.92 | Improved |
| Use MF instead of LBM (NILM) for fridge | feature-based NMF · 105 homes, fridge | RMS error in PEC: 2.69 -> 3.65 | Hurt |
| Use MF instead of kNN for HVAC | feature-based NMF · 516 homes, HVAC | RMS error in PEC: 11.96 -> 12.02 | Hurt |
| Use MF vs best NILM baselines for HVAC | feature-based NMF · 105 homes, HVAC | RMS error in PEC: 15.26 -> 12.53 | Improved |
| Add static household features (area, occupants, rooms) to matrix factorisation (ablation) | feature-based NMF · 105 homes, six appliances | relative % error reduction | Improved |
| Train on 516 homes with incomplete features instead of only 105 complete homes (plain MF) (ablation) | feature-based NMF · 105 test homes | relative % error reduction | Mixed |
Closest papers by meaning
- Transferring Decomposed Tensors for Scalable Energy Breakdown Across Regions (AAAI 2018 · similarity 0.89)
- Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates (ICML 2017 · similarity 0.83)
- BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting (NeurIPS 2023 · similarity 0.81)
- NeuralBES: A Differentiable, Control-Aware Emulator for Scalable Building Energy Modeling (NeurIPS 2026 · similarity 0.80)
- Building Timeseries Dataset: Empowering Large-Scale Building Analytics (NeurIPS 2024 · similarity 0.79)
- Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces (NeurIPS 2024 · similarity 0.78)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
