deep net loss landscape kernel spike random (and/or) noise kernel thermo- dynamic limit inverse temperature COVID {under, over}- parameterized inverse temperature mean field kernel mean field random (and/or) noise depth generalization NTK Hessian mean field empirical KRR numerics replica sparsity generative scaling deep net spike replica spike empirical two- layer Gaussian data depth How much time do I/we have? MNIST adversarial loss landscape {under, over}- parameterized. {under, over}- parameterized. How much time do I/we have? generative width width gradient descent eigen{value, vector, function} gradient descent eigen- {value, vector, function} generalization loss landscape numerics generative KRR MNIST COVID empirical width COVID deep net two- layer scaling thermo- dynamic limit inverse temperature KRR MNIST NTK gradient descent Gaussian data adversarial two- layer sparsity thermo- dynamic limit How much time do I/we have? sparsity random (and/or) noise numerics scaling Gaussian data generalization Hessian eigen{value, vector, function} adversarial replica Hessian NTK depth deep net loss landscape kernel spike random (and/or) noise kernel thermo- dynamic limit inverse temperature COVID {under, over}- parameterized inverse temperature mean field kernel mean field random (and/or) noise depth generalization NTK Hessian mean field empirical KRR numerics replica sparsity generative scaling deep net spike replica spike empirical two- layer Gaussian data depth How much time do I/we have? MNIST adversarial loss landscape {under, over}- parameterized. {under, over}- parameterized. How much time do I/we have? generative width width gradient descent eigen{value, vector, function} gradient descent eigen- {value, vector, function} generalization loss landscape numerics generative KRR MNIST COVID empirical width COVID deep net two- layer scaling thermo- dynamic limit inverse temperature KRR MNIST NTK gradient descent Gaussian data adversarial two- layer sparsity thermo- dynamic limit How much time do I/we have? sparsity random (and/or) noise numerics scaling Gaussian data generalization Hessian eigen{value, vector, function} adversarial replica Hessian NTK depth
(Print) Use this randomly generated list as your call list when playing the game. There is no need to say the BINGO column name. Place some kind of mark (like an X, a checkmark, a dot, tally mark, etc) on each cell as you announce it, to keep track. You can also cut out each item, place them in a bag and pull words from the bag.
deep net
loss landscape
kernel
spike
random (and/or) noise
kernel
thermo-dynamic limit
inverse temperature
COVID
{under, over}-parameterized
inverse temperature
mean field
kernel
mean field
random (and/or) noise
depth
generalization
NTK
Hessian
mean field
empirical
KRR
numerics
replica
sparsity
generative
scaling
deep net
spike
replica
spike
empirical
two-layer
Gaussian data
depth
How much time do I/we have?
MNIST
adversarial
loss landscape
{under, over}-parameterized.
{under, over}-parameterized.
How much time do I/we have?
generative
width
width
gradient descent
eigen{value, vector, function}
gradient descent
eigen-{value, vector, function}
generalization
loss landscape
numerics
generative
KRR
MNIST
COVID
empirical
width
COVID
deep net
two-layer
scaling
thermo-dynamic limit
inverse temperature
KRR
MNIST
NTK
gradient descent
Gaussian data
adversarial
two-layer
sparsity
thermo-dynamic limit
How much time do I/we have?
sparsity
random (and/or) noise
numerics
scaling
Gaussian data
generalization
Hessian
eigen{value, vector, function}
adversarial
replica
Hessian
NTK
depth