Results for "global minima"

Lowest possible loss.

Minimum relative to nearby points.

A wide basin often correlated with better generalization.

A narrow minimum often associated with poorer generalization.

Visualization of optimization landscape.

Techniques to understand model decisions (global or local), important in high-stakes and regulated settings.

Optimization with multiple local minima/saddle points; typical in neural networks.

Variability introduced by minibatch sampling during SGD.

Training across many devices/silos without centralizing raw data; aggregates updates, not data.

Optimization problems where any local minimum is global.

Attention mechanisms that reduce quadratic complexity.

Controls the size of parameter updates; too high diverges, too low trains slowly or gets stuck.

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

Number of samples per gradient update; impacts compute efficiency, generalization, and stability.

Nonlinear functions enabling networks to approximate complex mappings; ReLU variants dominate modern DL.

The shape of the loss function over parameter space.

Matrix of curvature information.

Planning via artificial force fields.

Mechanism that computes context-aware mixtures of representations; scales well and captures long-range dependencies.

Multiple agents interacting cooperatively or competitively.

Coordination arising without explicit programming.

Neural networks that operate on graph-structured data by propagating information along edges.

GNN framework where nodes iteratively exchange and aggregate messages from neighbors.

Pixel-wise classification of image regions.

Extension of convolution to graph domains using adjacency structure.

Transformer applied to image patches.

Distributed agents producing emergent intelligence.

Restricting updates to safe regions.

European regulation classifying AI systems by risk.

Deep learning system for protein structure prediction.