Deep Equilibrium Models: How Implicit Layers and Root-Finding Eliminate Activation Memory in Deep Learning
Deep Equilibrium Models: How Implicit Layers and Root-Finding Eliminate Activation Memory in Deep Learning Deep neural networks derive their expressive capacity from composition. In conventional architectures, depth is explicit: an input vector is transformed sequentially through a chain of $L$ discrete layers, each parameterized by dedicated weights. While effective, this paradigm creates a fundamental computational dependency where training memory scales linearly with network depth ($O(L)$) b
1 min