35 citations · 114 across the 25 of their papers we have counts for
30 papers
How Many Neurons Does it Take to Approximate the Maximum?
Itay Safran, Daniel Reichman, Paul Valiant
We study the size of a neural network needed to approximate the maximum function over inputs, in the most basic setting of approximating with respect to the norm, for con…
Inoculation strategies for bounded degree graphs
Mason DiCicco, Henry Poskanzer, Daniel Reichman
We analyze a game-theoretic abstraction of epidemic containment played on an undirected graph : each player is associated with a node in and can either acquire protection fr…
Size and depth of monotone neural networks: interpolation and approximation
Dan Mikulincer, Daniel Reichman
We study monotone neural networks with threshold gates where all the weights (other than the biases) are non-negative. We focus on the expressive power and efficiency of representa…
Local treewidth of random and noisy graphs with applications to stopping contagion in networks
Hermish Mehta, Daniel Reichman
We study the notion of local treewidth in sparse random graphs: the maximum treewidth over all -vertex subgraphs of an -vertex graph. When is not too large, we give nearl…
The Learning and Communication Complexity of Subsequence Containment
Mason DiCicco, Daniel Reichman
We consider the learning and communication complexity of subsequence containment. In the learning problem, we seek to learn a classifier that positively labels a binary string …
Size and Depth Separation in Approximating Benign Functions with Neural Networks
Gal Vardi, Daniel Reichman, Toniann Pitassi +1
When studying the expressive power of neural networks, a main challenge is to understand how the size and depth of the network affect its ability to approximate real functions. How…