Results for "distribution shift"

Measures how much information an observable random variable carries about unknown parameters.

Models that define an energy landscape rather than explicit probabilities.

Probabilistic model for sequential data with latent states.

Controls amount of noise added at each diffusion step.

Generative model that learns to reverse a gradual noise process.

Maintaining alignment under new conditions.

Performance drop when moving from simulation to reality.

Learning policies from expert demonstrations.

Restricting distribution of powerful models.

Methods that learn training procedures or initializations so models can adapt quickly to new tasks with little data.

Learning where data arrives sequentially and the model updates continuously, often under changing distributions.

The relationship between inputs and outputs changes over time, requiring monitoring and model updates.

The internal space where learned representations live; operations here often correlate with semantics or generative factors.

Techniques that discourage overly complex solutions to improve generalization (reduce overfitting).

Harmonic mean of precision and recall; useful when balancing false positives/negatives matters.

Scalar summary of ROC; measures ranking ability, not calibration.

Methods to set starting weights to preserve signal/gradient scales across layers.

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

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

When some classes are rare, requiring reweighting, resampling, or specialized metrics.

Model-generated content that is fluent but unsupported by evidence or incorrect; mitigated by grounding and verification.

Expanding training data via transformations (flips, noise, paraphrases) to improve robustness.

Artificially created data used to train/test models; helpful for privacy and coverage, risky if unrealistic.

Samples from the k highest-probability tokens to limit unlikely outputs.

Samples from the smallest set of tokens whose probabilities sum to p, adapting set size by context.

Raw model outputs before converting to probabilities; manipulated during decoding and calibration.

Reduction in uncertainty achieved by observing a variable; used in decision trees and active learning.

A narrow minimum often associated with poorer generalization.

Built-in assumptions guiding learning efficiency and generalization.

Strategy mapping states to actions.