Results for "variance control"

Error due to sensitivity to fluctuations in the training dataset.

A conceptual framework describing error as the sum of systematic error (bias) and sensitivity to data (variance).

Measure of spread around the mean.

Control using real-time sensor feedback.

Mathematical framework for controlling dynamic systems.

Control that remains stable under model uncertainty.

Control without feedback after execution begins.

Optimizes future actions using a model of dynamics.

Sampling from easier distribution with reweighting.

Continuous loop adjusting actions based on state feedback.

Algorithm computing control actions.

Finding control policies minimizing cumulative cost.

Human controlling robot remotely.

Classical controller balancing responsiveness and stability.

Control shared between human and agent.

Sum of independent variables converges to normal distribution.

Optimal control for linear systems with quadratic cost.

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

When a model fits noise/idiosyncrasies of training data and performs poorly on unseen data.

A robust evaluation technique that trains/evaluates across multiple splits to estimate performance variability.

Popular optimizer combining momentum and per-parameter adaptive step sizes via first/second moment estimates.

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

Systematic error introduced by simplifying assumptions in a learning algorithm.

Combines value estimation (critic) with policy learning (actor).

Diffusion model trained to remove noise step by step.

Controls amount of noise added at each diffusion step.

Vector whose direction remains unchanged under linear transformation.

Describes likelihoods of random variable outcomes.

Updated belief after observing data.

Approximating expectations via random sampling.