In this Section, we will present the projected gradient descent algorithms we use for our logistic and linear regression settings. We will use the following well known property of Projected Gradient Descent (Theorem 3.10 from ).
When the number of observations is smaller than what is needed for reconstruction, we can still ask whether there exists some Venn diagram that is consistent with the observations. Which classes of weighted graphs (or hypergraphs) can be represent…
We would like to thank Vasant Honavar who told us about the problems considered here and for several helpful discussions that were essential for us to complete this work.
There are several streams of literature in dynamic mechanism design. We begin with the stream that is closest to our work.
We provide algorithms that learn simple auctions whose revenue is approximately optimal in multi-item multi-bidder settings, for a wide range of valuations including unit-demand, additive, constrained additive, XOS, and subadditive. We obtain our le…
Given samples from an unknown distribution $p$ and a description of a distribution $q$, are $p$ and $q$ close or far? This question of "identity testing" has received significant attention in the case of testing whether $p$ and $q$ are equal or far …
We consider the problem of a revenue-maximizing seller with m items for sale to n additive bidders with hard budget constraints, assuming that the seller has some prior distribution over bidder values and budgets. The prior may be correlated across …
Since the initial conference publication of this work [DDS12a], some progress has been made on problems related to learning Poisson Binomial Distributions. The initial conference version [DDS12a] asked whether log-concave distributions over [n] (a g…
Credentials & highlights
- Project Views