Results 11  20
of
59
Discriminative Learning of BeamSearch Heuristics for Planning
 PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE 2007
, 2007
"... We consider the problem of learning heuristics for controlling forward statespace beam search in AI planning domains. We draw on a recent framework for “structured output classification ” (e.g. syntactic parsing) known as learning as search optimization (LaSO). The LaSO approach uses discriminative ..."
Abstract

Cited by 14 (3 self)
 Add to MetaCart
We consider the problem of learning heuristics for controlling forward statespace beam search in AI planning domains. We draw on a recent framework for “structured output classification ” (e.g. syntactic parsing) known as learning as search optimization (LaSO). The LaSO approach uses discriminative learning to optimize heuristic functions for searchbased computation of structured outputs and has shown promising results in a number of domains. However, the search problems that arise in AI planning tend to be qualitatively very different from those considered in structured classification, which raises a number of potential difficulties in directly applying LaSO to planning. In this paper, we discuss these issues and describe a LaSObased approach for discriminative learning of beamsearch heuristics in AI planning domains. We give convergence results for this approach and present experiments in several benchmark domains. The results show that the discriminatively trained heuristic can outperform the one used by the planner FF and another recent nondiscriminative learning approach.
Local search with very largescale neighborhoods for optimal permutations in machine translation
 In Proc. of the Workshop on Computationally Hard Problems and Joint Inference
, 2006
"... We introduce a novel decoding procedure for statistical machine translation and other ordering tasks based on a family of Very LargeScale Neighborhoods, some of which have previously been applied to other NPhard permutation problems. We significantly generalize these problems by simultaneously con ..."
Abstract

Cited by 13 (3 self)
 Add to MetaCart
(Show Context)
We introduce a novel decoding procedure for statistical machine translation and other ordering tasks based on a family of Very LargeScale Neighborhoods, some of which have previously been applied to other NPhard permutation problems. We significantly generalize these problems by simultaneously considering three distinct sets of ordering costs. We discuss how these costs might apply to MT, and some possibilities for training them. We show how to search and sample from exponentially large neighborhoods using efficient dynamic programming algorithms that resemble statistical parsing. We also incorporate techniques from statistical parsing to improve the runtime of our search. Finally, we report results of preliminary experiments indicating that the approach holds promise. 1
A memorybased rash optimizer
 IN AAAI06 WORKSHOP ON HEURISTIC SEARCH, MEMORY BASED HEURISTICS AND THEIR APPLICATIONS
, 2006
"... This paper presents a memorybased Reactive Affine Shaker (MRASH) algorithm for global optimization. The Reactive Affine Shaker is an adaptive search algorithm based only on the function values. MRASH is an extension of RASH in which good starting points to RASH are suggested online by using Bayes ..."
Abstract

Cited by 10 (2 self)
 Add to MetaCart
(Show Context)
This paper presents a memorybased Reactive Affine Shaker (MRASH) algorithm for global optimization. The Reactive Affine Shaker is an adaptive search algorithm based only on the function values. MRASH is an extension of RASH in which good starting points to RASH are suggested online by using Bayesian Locally Weighted Regression (BLWR). Both techniques use the memory about the previous history of the search to guide the future exploration but in very different ways. RASH compiles the previous experience into a local search area where sample points are drawn, while locallyweighted regression saves the entire previous history to be mined extensively when an additional sample point is generated. Because of the high computational cost related to the BLWR model, it is applied only to evaluate the potential of an initial point for a local search run. The experimental results, focussed onto the case when the dominant computational cost is the evaluation of the target f function, show that MRASH is indeed capable of leading to good results for a smaller number of function evaluations.
Structured Prediction via Output Space Search
 Journal of Machine Learning Research (JMLR
, 2014
"... We consider a framework for structured prediction based on search in the space of complete structured outputs. Given a structured input, an output is produced by running a timebounded search procedure guided by a learned cost function, and then returning the least cost output uncovered during the s ..."
Abstract

Cited by 9 (4 self)
 Add to MetaCart
We consider a framework for structured prediction based on search in the space of complete structured outputs. Given a structured input, an output is produced by running a timebounded search procedure guided by a learned cost function, and then returning the least cost output uncovered during the search. This framework can be instantiated for a wide range of search spaces and search procedures, and easily incorporates arbitrary structuredprediction loss functions. In this paper, we make two main technical contributions. First, we describe a novel approach to automatically defining an effective search space over structured outputs, which is able to leverage the availability of powerful classification learning algorithms. In particular, we define the limiteddiscrepancy search space and relate the quality of that space to the quality of learned classifiers. We also define a sparse version of the search space to improve the efficiency of our overall approach. Second, we give a generic cost function learning approach that is applicable to a wide range of search procedures. The key idea is to learn a cost function that attempts to mimic the behavior of conducting searches guided by the true loss function. Our experiments on six benchmark domains show that a small amount of search in limited discrepancy search space is often sufficient for significantly improving on stateoftheart structuredprediction performance. We also demonstrate significant speed improvements for our approach using sparse search spaces with little or no loss in accuracy.
Learning an Approximation to Inductive Logic Programming Clause Evaluation
 In Proceedings of the 14th international
, 2004
"... One challenge faced by many Inductive Logic Programming (ILP) systems is poor scalability to problems with large search spaces and many examples. Randomized search methods such as stochastic clause selection (SCS) and rapid random restarts (RRR) have proven somewhat successful at addressing this ..."
Abstract

Cited by 8 (1 self)
 Add to MetaCart
(Show Context)
One challenge faced by many Inductive Logic Programming (ILP) systems is poor scalability to problems with large search spaces and many examples. Randomized search methods such as stochastic clause selection (SCS) and rapid random restarts (RRR) have proven somewhat successful at addressing this weakness. However, on datasets where hypothesis evaluation is computationally expensive, even these algorithms may take unreasonably long to discover a good solution. We attempt to improve the performance of these algorithms on datasets by learning an approximation to ILP hypothesis evaluation. We generate a small set of hypotheses, uniformly sampled from the space of candidate hypotheses, and evaluate this set on actual data. These hypotheses and their corresponding evaluation scores serve as training data for learning an approximate hypothesis evaluator. We outline three techniques that make use of the trained evaluationfunction approximator in order to reduce the computation required during an ILP hypothesis search. We test our approximate clause evaluation algorithm using the popular ILP system Aleph.
HCsearch: A learning framework for searchbased structured prediction
 JAIR
"... Structured prediction is the problem of learning a function that maps structured inputs to structured outputs. Prototypical examples of structured prediction include partofspeech tagging and semantic segmentation of images. Inspired by the recent successes of searchbased structured prediction, we ..."
Abstract

Cited by 7 (3 self)
 Add to MetaCart
(Show Context)
Structured prediction is the problem of learning a function that maps structured inputs to structured outputs. Prototypical examples of structured prediction include partofspeech tagging and semantic segmentation of images. Inspired by the recent successes of searchbased structured prediction, we introduce a new framework for structured prediction called HCSearch. Given a structured input, the framework uses a search procedure guided by a learned heuristic H to uncover high quality candidate outputs and then employs a separate learned cost function C to select a final prediction among those outputs. The overall loss of this prediction architecture decomposes into the loss due to H not leading to high quality outputs, and the loss due to C not selecting the best among the generated outputs. Guided by this decomposition, we minimize the overall loss in a greedy stagewise manner by first training H to quickly uncover high quality outputs via imitation learning, and then training C to correctly rank the outputs generated via H according to their true losses. Importantly, this training procedure is sensitive to the particular loss function of interest and the timebound allowed for predictions. Experiments on several benchmark domains show that our approach significantly outperforms several stateoftheart methods. 1.
Reactive Search Optimization: Learning while Optimizing
"... The final purpose of Reactive Search Optimization (RSO) is to simplify the life for the final user of optimization. While researchers enjoy designing algorithms, testing alternatives, tuning parameters and choosing solution schemes — in fact this is part of their daily life — the final users ’ inter ..."
Abstract

Cited by 7 (3 self)
 Add to MetaCart
(Show Context)
The final purpose of Reactive Search Optimization (RSO) is to simplify the life for the final user of optimization. While researchers enjoy designing algorithms, testing alternatives, tuning parameters and choosing solution schemes — in fact this is part of their daily life — the final users ’ interests are different: solving a problem in the
Feature selection methods for improving protein structure prediction with Rosetta
 in: Advances in Neural Information Processing Systems (NIPS
, 2007
"... Rosetta is one of the leading algorithms for protein structure prediction today. It is a Monte Carlo energy minimization method requiring many random restarts to find structures with low energy. In this paper we present a resampling technique for structure prediction of small alpha/beta proteins usi ..."
Abstract

Cited by 7 (3 self)
 Add to MetaCart
(Show Context)
Rosetta is one of the leading algorithms for protein structure prediction today. It is a Monte Carlo energy minimization method requiring many random restarts to find structures with low energy. In this paper we present a resampling technique for structure prediction of small alpha/beta proteins using Rosetta. From an initial round of Rosetta sampling, we learn properties of the energy landscape that guide a subsequent round of sampling toward lowerenergy structures. Rather than attempt to fit the full energy landscape, we use feature selection methods—both L1regularized linear regression and decision trees—to identify structural features that give rise to low energy. We then enrich these structural features in the second sampling round. Results are presented across a benchmark set of nine small alpha/beta proteins demonstrating that our methods seldom impair, and frequently improve, Rosetta’s performance. 1
Generating SAT LocalSearch Heuristics using a GP HyperHeuristic Framework
"... Abstract. We present GPHH, a framework for evolving localsearch 3SAT heuristics based on GP. The aim is to obtain “disposable ” heuristics which are evolved and used for a specific subset of instances of a problem. We test the heuristics evolved by GPHH against wellknown localsearch heuristics ..."
Abstract

Cited by 6 (0 self)
 Add to MetaCart
(Show Context)
Abstract. We present GPHH, a framework for evolving localsearch 3SAT heuristics based on GP. The aim is to obtain “disposable ” heuristics which are evolved and used for a specific subset of instances of a problem. We test the heuristics evolved by GPHH against wellknown localsearch heuristics on a variety of benchmark SAT problems. Results are very encouraging. 1
Local Search Methods
, 2006
"... Local search is one of the fundamental paradigms for solving computationally hard combinatorial problems, including the constraint satisfaction problem (CSP). It provides the basis for some of the most successful and versatile methods for solving the large and difficult problem instances encountered ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
Local search is one of the fundamental paradigms for solving computationally hard combinatorial problems, including the constraint satisfaction problem (CSP). It provides the basis for some of the most successful and versatile methods for solving the large and difficult problem instances encountered in many reallife applications. Despite impressive advances in systematic, complete search algorithms, local search methods in many cases represent the only feasible way for solving these large and complex instances. Local search algorithms are also naturally suited for dealing with the optimisation criteria arising in many practical applications. The basic idea underlying local search is to start with a randomly or heuristically generated candidate solution of a given problem instance, which may be infeasible, suboptimal or incomplete, and to iteratively improve this candidate solution by means of typically minor modifications. Different local search methods vary in the way in which improvements are achieved, and in particular, in the way in which situations are handled in which no direct improvement is possible. Most local search methods use randomisation to ensure that the search process does not