Results for "statistical learning"

AI discovering new compounds/materials.

Generates sequences one token at a time, conditioning on past tokens.

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

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

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

Framework for identifying, measuring, and mitigating model risks.

Probabilistic model for sequential data with latent states.

Sample mean converges to expected value.

Sum of independent variables converges to normal distribution.

Eliminating variables by integrating over them.

Assigning AI costs to business units.

Guaranteed response times.

AI-driven buying/selling of financial assets.

Mechanics of price formation.

Quantifying financial risk.

Maximum expected loss under normal conditions.

Risk of incorrect financial models.

Modeling chemical systems computationally.

Signals indicating dangerous behavior.

Adjusting learning rate over training to improve convergence.

Ordering training samples from easier to harder to improve convergence or generalization.

Selecting the most informative samples to label (e.g., uncertainty sampling) to reduce labeling cost.

Learning from data generated by a different policy.

Learning a function from input-output pairs (labeled data), optimizing performance on predicting outputs for unseen inputs.

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

A model is PAC-learnable if it can, with high probability, learn an approximately correct hypothesis from finite samples.

Learning policies from expert demonstrations.

Learning structure from unlabeled data, such as discovering groups, compressing representations, or modeling data distributions.

A branch of ML using multi-layer neural networks to learn hierarchical representations, often excelling in vision, speech, and language.

A learning paradigm where an agent interacts with an environment and learns to choose actions to maximize cumulative reward.