• Publications
  • Influence
Object Detection with Discriminatively Trained Part Based Models
We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in
Policy Gradient Methods for Reinforcement Learning with Function Approximation
TLDR
This paper proves for the first time that a version of policy iteration with arbitrary differentiable function approximation is convergent to a locally optimal policy.
A discriminatively trained, multiscale, deformable part model
TLDR
A discriminatively trained, multiscale, deformable part model for object detection, which achieves a two-fold improvement in average precision over the best performance in the 2006 PASCAL person detection challenge and outperforms the best results in the 2007 challenge in ten out of twenty categories.
Cascade object detection with deformable part models
TLDR
In analogy to probably approximately correct (PAC) learning, the notion of probably approximately admissible (PAA) thresholds is introduced, providing theoretical guarantees on the performance of the cascade method and can be computed from a small sample of positive examples.
Resolution Theorem Proving
Some PAC-Bayesian Theorems
TLDR
The PAC-Bayesian theorems given here apply to an arbitrary prior measure on an arbitrary concept space and provide an alternative to the use of VC dimension in proving PAC bounds for parameterized concepts.
Systematic Nonlinear Planning
TLDR
A simple, sound, complete, and systematic algorithm for domain independent STRIPS planning by starting with a ground procedure and then applying a general, and independently verifiable, lifting transformation.
Evidence for Invariants in Local Search
TLDR
This work presents two statistical measures of the local search process that allow one to quickly find the optimal noise settings, and applies these principles to the problem of evaluating new search heuristics, and discovered two promising new strategies.
A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks
TLDR
A generalization bound for feedforward neural networks is presented in terms of the product of the spectral norm of the layers and the Frobeniusnorm of the weights using a PAC-Bayes analysis.
...
...