Tagged “evaluation-mlops”

6 posts.

All Model Architecture23 Training & Alignment22 Inference & Serving24 Agents & Orchestration13 Reasoning & Evaluation28 Safety, Security & Governance9 Platforms & Practice22

Platforms & Practice 30 min

Drift Is Not Decay: What Production Shift Detectors Actually Tell You

The industry monitors input distributions because inputs are what it has. But a drift alarm is neither necessary nor sufficient for a model getting worse, and forty features tested daily at alpha 0.05 fire on a healthy system 87%…

ml-observability drift distribution-shift monitoring ∑ ◫

Platforms & Practice 27 min

Four Ways an A/B Test Lies: Power, Peeking, Sample Ratio Mismatch and Interference

At Microsoft, roughly one third of tested ideas move the metric in the intended direction. That number is only meaningful if the tests are trustworthy, and the four failure modes that destroy trustworthiness all produce a clean, …

experimentation ab-testing causal-inference statistics ∑ ◫

Reasoning & Evaluation 24 min

Hidden Technical Debt, a Decade On: What Continuous Delivery for ML Actually Fixed

In 2015 a Google paper catalogued the ways machine learning systems rot, and a decade of MLOps tooling set out to pay that debt down. It paid down the debt that lives in pipelines and artefacts, and left the debt that lives in ju…

ci-cd-for-ml mlops evaluation-mlops deployment ∑ ◫

Platforms & Practice 24 min

Reading Its Own Handwriting: Position Bias, Feedback Loops and Counterfactual Correction

Move a document from rank 5 to rank 1 and its click-through rate jumps without its relevance changing at all. Train on those clicks and the model learns position, which the previous ranker chose, which means it learns to imitate …

ranking recommender-systems learning-to-rank counterfactual ∑ ◫

Platforms & Practice 25 min

The Controls That Make It Worse: Colliders, Mediators and Why Adjusting for Everything Is Wrong

Open surgery beat percutaneous nephrolithotomy on small kidney stones, 93% to 87%. It beat it on large stones too, 73% to 69%. Pooled across both, it lost, 78% to 83%. The arithmetic is correct in all three statements, and no amo…

causal-inference statistics confounding dags ∑ ◫

Reasoning & Evaluation 23 min

The Progress Illusion in Recommender Systems: Weak Baselines, Sampled Metrics and Leaky Splits

In 2019 a careful team could reproduce only 7 of 18 neural recommenders from top venues, and 6 of those 7 lost to nearest-neighbour heuristics. The models were not the problem. The protocol was: untuned baselines, metrics compute…

recommender-systems evaluation metrics benchmarks ∑ ◫