Results for "outcome prediction"

What would have happened under different conditions.

Predicting case success probabilities.

Variable enabling causal inference despite confounding.

Shift in model outputs.

Feature attribution method grounded in cooperative game theory for explaining predictions in tabular settings.

Training objective where the model predicts the next token given previous tokens (causal modeling).

A proper scoring rule measuring squared error of predicted probabilities for binary outcomes.

Controlled experiment comparing variants by random assignment to estimate causal effects of changes.

Coordinating tools, models, and steps (retrieval, calls, validation) to deliver reliable end-to-end behavior.

Average value under a distribution.

Models effects of interventions (do(X=x)).

Continuous loop adjusting actions based on state feedback.

Designing systems where rational agents behave as desired.

Trend reversal when data is aggregated improperly.

A model that assigns probabilities to sequences of tokens; often trained by next-token prediction.

Probabilistic graphical model for structured prediction.

Monte Carlo method for state estimation.

Low-latency prediction per request.

Learning by minimizing prediction error.

Deep learning system for protein structure prediction.

A function measuring prediction error (and sometimes calibration), guiding gradient-based optimization.

Studying internal mechanisms or input influence on outputs (e.g., saliency maps, SHAP, attention analysis).

Networks with recurrent connections for sequences; largely supplanted by Transformers for many tasks.

Local surrogate explanation method approximating model behavior near a specific input.

Inputs crafted to cause model errors or unsafe behavior, often imperceptible in vision or subtle in text.

Error due to sensitivity to fluctuations in the training dataset.

Systematic error introduced by simplifying assumptions in a learning algorithm.

GNN framework where nodes iteratively exchange and aggregate messages from neighbors.

Extension of convolution to graph domains using adjacency structure.

Graphs containing multiple node or edge types with different semantics.