
Acceleration via Fractal Learning Rate Schedules
When balancing the practical tradeoffs of iterative methods for largesc...
read it

Tight Hardness Results for Training Depth2 ReLU Networks
We prove several hardness results for training depth2 neural networks w...
read it

From Boltzmann Machines to Neural Networks and Back Again
Graphical models are powerful tools for modeling highdimensional data, ...
read it

StatisticalQuery Lower Bounds via Functional Gradients
We give the first statisticalquery lower bounds for agnostically learni...
read it

Superpolynomial Lower Bounds for Learning OneLayer Neural Networks using Gradient Descent
We prove the first superpolynomial lower bounds for learning onelayer n...
read it

Approximation Schemes for ReLU Regression
We consider the fundamental problem of ReLU regression, where the goal i...
read it

Efficiently Learning Adversarially Robust Halfspaces with Noise
We study the problem of learning adversarially robust halfspaces in the ...
read it

Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals
We consider the problem of computing the bestfitting ReLU with respect ...
read it

Learning Restricted Boltzmann Machines with Arbitrary External Fields
We study the problem of learning graphical models with latent variables....
read it

Disentangling Mixtures of Epidemics on Graphs
We consider the problem of learning the weighted edges of a mixture of t...
read it

Learning Two layer Networks with Multinomial Activation and High Thresholds
Giving provable guarantees for learning neural networks is a core challe...
read it

Quantifying Perceptual Distortion of Adversarial Examples
Recent work has shown that additive threat models, which only permit the...
read it

Learning Ising Models with Independent Failures
We give the first efficient algorithm for learning the structure of an I...
read it

Improved Learning of Onehiddenlayer Convolutional Neural Networks with Overlaps
We propose a new algorithm to learn a onehiddenlayer convolutional neu...
read it

Learning One Convolutional Layer with Overlapping Patches
We give the first provably efficient algorithm for learning a one hidden...
read it

Learning DepthThree Neural Networks in Polynomial Time
We give a polynomialtime algorithm for learning neural networks with on...
read it
Surbhi Goel
is this you? claim profile