• Publications
  • Influence
Learning Prices for Repeated Auctions with Strategic Buyers
TLDR
Inspired by real-time ad exchanges for online display advertising, we consider the problem of inferring a buyer's value distribution for a good when the buyer is repeatedly interacting with a seller through a posted-price mechanism. Expand
  • 98
  • 23
  • PDF
Repeated Contextual Auctions with Strategic Buyers
TLDR
We give the first algorithm attaining sublinear regret in the contextual setting against a surplus-maximizing buyer. Expand
  • 75
  • 15
  • PDF
Budget Optimization for Sponsored Search: Censored Learning in MDPs
TLDR
We cast the budget optimization problem as a Markov Decision Process (MDP) with censored observations, and propose a learning algorithm based on the well-known Kaplan-Meier or product-limit estimator. Expand
  • 74
  • 7
  • PDF
Repeated Inverse Reinforcement Learning
TLDR
We introduce a novel repeated Inverse Reinforcement Learning problem: the agent has to act on behalf of a human in a sequence of tasks and wishes to minimize the number of tasks that it surprises the human by acting suboptimally. Expand
  • 32
  • 6
  • PDF
Learning from Contagion (Without Timestamps)
TLDR
We introduce and study new models for learning from contagion processes in a network. Expand
  • 17
  • 4
  • PDF
Bandits, Query Learning, and the Haystack Dimension
TLDR
We give an analysis of the query complexity of this problem, under the assumption that the payo of each arm is given by a function belonging to a known, nite, but otherwise arbitrary function class. Expand
  • 21
  • 3
  • PDF
A moving target defense approach to mitigate DDoS attacks against proxy-based architectures
TLDR
We show that current solutions are vulnerable to a new type of attack, the proxy harvesting attack, and propose a moving target defense technique consisting in periodically and proactively replacing one or more proxies and remapping clients to proxies. Expand
  • 39
  • 2
  • PDF
Answering with Cases: A CBR Approach to Deep Learning
TLDR
We present a hybrid Textual Case-based reasoning (hTCBR) approach using Deep Neural Networks and Big Data Technologies. Expand
  • 15
  • 2
  • PDF
Online Learning and Profit Maximization from Revealed Preferences
TLDR
We give an efficient algorithm for the merchant's problem that consists of a learning phase in which the consumer's utility function is (perhaps partially) inferred, followed by a price optimization step. Expand
  • 23
  • 2
  • PDF
Budgeted Prediction with Expert Advice
TLDR
We consider a budgeted variant of the problem of learning from expert advice with N experts. Expand
  • 18
  • 2
  • PDF