Research

My main current topics of interest are:

• machine learning
• theory and algorithms
• speech processing
• weighted automata theory and algorithms
• string or sequence algorithms
• natural language processing
• computational biology

Some recent talks:

• Learning with Data-Dependent Hypothesis sets (video).
• Regret Minimization against Strategic Buyers.
• AdaNet: adaptive learning of neural networks.
• Online Learning for Time Series Prediction.
• Learning Weighted Automata.
• Time Series Prediction and Online Learning.
• Structured Prediction Theory and Algorithms.
• On-Line Learning with Path Experts and Non-Additive Losses.
• Deep Boosting.
• Learning Theory and Algorithms for Second-Price Auctions with Reserve.

The following are some selected topics with a list of publications:

• time series
• auctioning
• boosting
• domain adaptation and sample bias correction
• ranking
• learning kernels
• low-rank approximation
• transductive inference
• rational kernels
• shortest-distance algorithms
• speech recognition
• weighted automata and transducers