3 problems

Global-minimum and strict-saddle conjecture for the third-layer synaptic objective
Let $X \in \mathbb{R}^{n \times T}$ satisfy $C_X \succ 0$ , and let $W(t)$ follow the continuous-time gradient-flow feedforward synaptic dynamics. Let $\mathcal{S}$ denote the stati…
opengradient-flows hebbian-learning optimization-landscapes
0 responses
03
Conjecture on two-dimensional loss landscapes of wide neural networks
Let $F$ be the loss of a neural network and let $\theta^*$ be a global minimum. Choose two vectors $v_1,v_2$ according to a specified rule, for example a Gaussian distribution, and…
openneural-networks optimization-landscapes residual-networks
0 responses
07
Conjecture on gradient-descent performance in overparameterized neural networks
Gradient-descent performance conjecture. For a proper constant $\eta$ , and for a random initial point drawn from a certain distribution, such as Xavier initialization,
opengradient-descent neural-networks optimization-landscapes
0 responses
06

Global-minimum and strict-saddle conjecture for the third-layer synaptic objective