We study a generalization of boosting to the multiclass setting. We intr...
We present a PTAS for learning random constant-depth networks. We show t...
Understanding when neural networks can be learned efficiently is a
funda...
We investigate the sample complexity of bounded two-layer neural network...
Recently, Daniely and Granot [arXiv:1910.05697] introduced a new notion ...
The amount of training-data is one of the key factors which determines t...
We consider stochastic optimization with delayed gradients where, at eac...
As machine learning increasingly becomes more prevalent in our everyday ...
We prove hardness-of-learning results under a well-studied assumption on...
We consider ReLU networks with random weights, in which the dimension
de...
Neural networks are nowadays highly successful despite strong hardness
r...
We prove that a single step of gradient decent over depth two network, w...
In recent years we see a rapidly growing line of research which shows
le...
Recent advances in randomized incremental methods for minimizing L-smoot...
Many results in recent years established polynomial time learnability of...
We investigate the sample complexity of networks with bounds on the magn...
A leading hypothesis for the surprising generalization of neural network...
Since its inception in the 1980s, ID3 has become one of the most success...
In recent years, there are many attempts to understand popular heuristic...
We consider online algorithms under both the competitive ratio criteria ...
One of the key resources in large-scale learning systems is the number o...
In many practical uses of reinforcement learning (RL) the set of actions...
Complex classifiers may exhibit "embarassing" failures in cases that wou...
We show that the standard stochastic gradient decent (SGD) algorithm is
...
Let f:S^d-1×S^d-1→S be a function of
the form f(x,x') = g(〈x,x'〉)
for g:...
We develop a general duality between neural networks and compositional
k...