Results for "data distribution"
Learning where data arrives sequentially and the model updates continuously, often under changing distributions.
Methods that learn training procedures or initializations so models can adapt quickly to new tasks with little data.
A mismatch between training and deployment data distributions that can degrade model performance.
A scalar measure optimized during training, typically expected loss over data, sometimes with regularization terms.
When a model cannot capture underlying structure, performing poorly on both training and test data.
A conceptual framework describing error as the sum of systematic error (bias) and sensitivity to data (variance).
Separating data into training (fit), validation (tune), and test (final estimate) to avoid leakage and optimism bias.
Letting an LLM call external functions/APIs to fetch data, compute, or take actions, improving reliability.
Updating a pretrained model’s weights on task-specific data to improve performance or adapt style/behavior.
Reinforcement learning from human feedback: uses preference data to train a reward model and optimize the policy.
Systematic differences in model outcomes across groups; arises from data, labels, and deployment context.
A formal privacy framework ensuring outputs do not reveal much about any single individual’s data contribution.
Standardized documentation describing intended use, performance, limitations, data, and ethical considerations.
Systematic review of model/data processes to ensure performance, fairness, security, and policy compliance.
Automated testing and deployment processes for models and data workflows, extending DevOps to ML artifacts.
Logging hyperparameters, code versions, data snapshots, and results to reproduce and compare experiments.
Ability to replicate results given same code/data; harder in distributed training and nondeterministic ops.
Attacks that manipulate model instructions (especially via retrieved content) to override system goals or exfiltrate data.
Attacks that infer whether specific records were in training data, or reconstruct sensitive training examples.
Methods to protect model/data during inference (e.g., trusted execution environments) from operators/attackers.
Estimating parameters by maximizing likelihood of observed data.
Empirical laws linking model size, data, compute to performance.
Learning from data generated by a different policy.
Learning only from current policy’s data.
Recovering training data from gradients.
Inferring sensitive features of training data.
Detecting unauthorized model outputs or data leaks.
Neural networks that operate on graph-structured data by propagating information along edges.
Probabilistic model for sequential data with latent states.
Models that learn to generate samples resembling training data.