Results for "dynamics learning"

Flat high-dimensional regions slowing training.

Optimization under uncertainty.

Model trained on its own outputs degrades quality.

Learning action mapping directly from demonstrations.

Identifying suspicious transactions.

Awareness and regulation of internal processes.

A mismatch between training and deployment data distributions that can degrade model performance.

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

A parameterized mapping from inputs to outputs; includes architecture + learned parameters.

Configuration choices not learned directly (or not typically learned) that govern training or architecture.

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

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

A gradient method using random minibatches for efficient training on large datasets.

Activation max(0, x); improves gradient flow and training speed in deep nets.

Gradients shrink through layers, slowing learning in early layers; mitigated by ReLU, residuals, normalization.

Techniques that stabilize and speed training by normalizing activations; LayerNorm is common in Transformers.

Updating a pretrained model’s weights on task-specific data to improve performance or adapt style/behavior.

A preference-based training method optimizing policies directly from pairwise comparisons without explicit RL loops.

Model trained to predict human preferences (or utility) for candidate outputs; used in RLHF-style pipelines.

Systematic differences in model outcomes across groups; arises from data, labels, and deployment context.

Rules and controls around generation (filters, validators, structured outputs) to reduce unsafe or invalid behavior.

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

Measure of consistency across labelers; low agreement indicates ambiguous tasks or poor guidelines.

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

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

Policies and practices for approving, monitoring, auditing, and documenting models in production.

Standardized documentation describing intended use, performance, limitations, data, and ethical considerations.

Techniques that fine-tune small additional components rather than all weights to reduce compute and storage.

Structured dataset documentation covering collection, composition, recommended uses, biases, and maintenance.

PEFT method injecting trainable low-rank matrices into layers, enabling efficient fine-tuning.