Research map / Learning theory and algorithms / Fairness
T-TAMER: Provably Taming Trade-offs in ML Serving
Yuanyuan Chloe Yang, Ruimin Zhang, Jamie Heather Morgenstern, Haifeng Xu
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 |
|---|---|---|---|
| allow recall (revisiting earlier sub-models) instead of no-recall confidence-threshold exit (ablation) | cascaded early-exit inference · directed-line costly exploration (theory) | approximation ratio to optimum | Improved |
| use dynamic indexing strategy with recall on vision early-exit | T-Tamer Recall · video streaming classification, VGG-11/13 | latency vs accuracy: latency 45% of original with under 7% accuracy loss | Improved |
| use dynamic indexing strategy with recall on NLP early-exit | T-Tamer Recall · IMDB and Amazon Review, BERT-base and GPT-2 | latency: latency reduced by up to 90% | Improved |
Closest papers by meaning
- Leaving the Nest: Going beyond Local Loss Functions for Predict-Then-Optimize (AAAI 2024 · similarity 0.85)
- Gatekeeper: Improving Model Cascades Through Confidence Tuning (NeurIPS 2025 · similarity 0.84)
- Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers (NeurIPS 2025 · similarity 0.84)
- Causal LLM Routing: End-to-End Regret Minimization from Observational Data (NeurIPS 2025 · similarity 0.84)
- A Hitchhiker's Guide to Scaling Law Estimation (ICML 2025 · similarity 0.84)
- Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data (ICLR 2025 · similarity 0.83)
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.
