{"version":"1.0","type":"rich","provider_name":"gaks.ai AI Glossary","provider_url":"https://gaks.ai/glossary","title":"Stochastic Gradient Descent — AI Glossary","author_name":"Glenn Katrud Solheim","author_url":"https://gaks.ai","width":600,"height":200,"html":"<div style=\"font-family:sans-serif;border:1px solid #e0e0e0;border-radius:8px;padding:16px;max-width:600px;background:#ffffff;color:#111111;\"><p style=\"margin:0 0 4px;font-size:11px;color:#666;\">AI Glossary — gaks.ai</p><h3 style=\"margin:0 0 8px;font-size:16px;\">Stochastic Gradient Descent (SGD)</h3><p style=\"margin:0 0 12px;font-size:14px;line-height:1.6;\">A variant of gradient descent that updates model weights using the gradient computed from a single data point or small batch, rather than the full dataset. The randomness this introduces is not just a computational shortcut, it can help models escape flat or suboptimal regions of the loss landscape that full-batch gradient descent might get stuck in, and it scales far more efficiently to large datasets.</p><a href=\"https://gaks.ai/glossary/stochastic-gradient-descent\" style=\"font-size:12px;color:#0077aa;\">Source: gaks.ai/glossary/stochastic-gradient-descent →</a></div>"}