KRR two- layer MNIST two- layer deep net eigen{value, vector, function} generalization width adversarial generative spike depth mean field spike kernel sparsity generalization loss landscape two- layer KRR kernel Gaussian data empirical generative replica thermo- dynamic limit gradient descent MNIST scaling gradient descent generalization eigen- {value, vector, function} mean field inverse temperature deep net replica {under, over}- parameterized KRR thermo- dynamic limit {under, over}- parameterized. NTK NTK spike thermo- dynamic limit NTK numerics numerics deep net replica loss landscape random (and/or) noise width eigen{value, vector, function} Hessian sparsity How much time do I/we have? inverse temperature {under, over}- parameterized. COVID random (and/or) noise empirical random (and/or) noise depth scaling COVID loss landscape gradient descent MNIST How much time do I/we have? Gaussian data How much time do I/we have? Hessian width Hessian COVID Gaussian data empirical sparsity mean field inverse temperature adversarial adversarial generative numerics kernel depth scaling KRR two- layer MNIST two- layer deep net eigen{value, vector, function} generalization width adversarial generative spike depth mean field spike kernel sparsity generalization loss landscape two- layer KRR kernel Gaussian data empirical generative replica thermo- dynamic limit gradient descent MNIST scaling gradient descent generalization eigen- {value, vector, function} mean field inverse temperature deep net replica {under, over}- parameterized KRR thermo- dynamic limit {under, over}- parameterized. NTK NTK spike thermo- dynamic limit NTK numerics numerics deep net replica loss landscape random (and/or) noise width eigen{value, vector, function} Hessian sparsity How much time do I/we have? inverse temperature {under, over}- parameterized. COVID random (and/or) noise empirical random (and/or) noise depth scaling COVID loss landscape gradient descent MNIST How much time do I/we have? Gaussian data How much time do I/we have? Hessian width Hessian COVID Gaussian data empirical sparsity mean field inverse temperature adversarial adversarial generative numerics kernel depth scaling
(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.
KRR
two-layer
MNIST
two-layer
deep net
eigen{value, vector, function}
generalization
width
adversarial
generative
spike
depth
mean field
spike
kernel
sparsity
generalization
loss landscape
two-layer
KRR
kernel
Gaussian data
empirical
generative
replica
thermo-dynamic limit
gradient descent
MNIST
scaling
gradient descent
generalization
eigen-{value, vector, function}
mean field
inverse temperature
deep net
replica
{under, over}-parameterized
KRR
thermo-dynamic limit
{under, over}-parameterized.
NTK
NTK
spike
thermo-dynamic limit
NTK
numerics
numerics
deep net
replica
loss landscape
random (and/or) noise
width
eigen{value, vector, function}
Hessian
sparsity
How much time do I/we have?
inverse temperature
{under, over}-parameterized.
COVID
random (and/or) noise
empirical
random (and/or) noise
depth
scaling
COVID
loss landscape
gradient descent
MNIST
How much time do I/we have?
Gaussian data
How much time do I/we have?
Hessian
width
Hessian
COVID
Gaussian data
empirical
sparsity
mean field
inverse temperature
adversarial
adversarial
generative
numerics
kernel
depth
scaling