6 appearances on the backlist front page in the last 30 days.
Past theory used ODEs or local bounds that only apply once you arrive at the edge. To solve the global problem, we introduce the "edge coupling,” a discrete generating function imported from Hamiltonian mechanics whose criticality condition
Differencing this condition and invoking a conservation law argument, we can show mathematically that sharpness rises to 2/lr. This means the cause of EoS is an inescapable artifact of discrete optimization, not a property of neural network
Gradient descent on neural networks frequently drives the sharpest Hessian eigenvalue to exactly 2/learning_rate. This is the Edge of Stability. For five years, ML theory has failed to explain why this happens globally from any initializati
Past theory used ODEs or local bounds that only apply once you arrive at the edge. To solve the global problem, we introduce the "edge coupling,” a discrete generating function imported from Hamiltonian mechanics whose criticality condition
Differencing this condition and invoking a conservation law argument, we can show mathematically that sharpness rises to 2/lr. This means the cause of EoS is an inescapable artifact of discrete optimization, not a property of neural network
Gradient descent on neural networks frequently drives the sharpest Hessian eigenvalue to exactly 2/learning_rate. This is the Edge of Stability. For five years, ML theory has failed to explain why this happens globally from any initializati