Goto

Collaborating Authors

Search: Instructional Materials


Variational Beam Search for Online Learning with Distribution Shifts

arXiv.org Machine Learning

We consider the problem of online learning in the presence of sudden distribution shifts as frequently encountered in applications such as autonomous navigation. Distribution shifts require constant performance monitoring and re-training. They may also be hard to detect and can lead to a slow but steady degradation in model performance. To address this problem we propose a new Bayesian meta-algorithm that can both (i) make inferences about subtle distribution shifts based on minimal sequential observations and (ii) accordingly adapt a model in an online fashion. The approach uses beam search over multiple change point hypotheses to perform inference on a hierarchical sequential latent variable modeling framework. Our proposed approach is model-agnostic, applicable to both supervised and unsupervised learning, and yields significant improvements over state-of-the-art Bayesian online learning approaches.


Online learning with dynamics: A minimax perspective

arXiv.org Machine Learning

We study the problem of online learning with dynamics, where a learner interacts with a stateful environment over multiple rounds. In each round of the interaction, the learner selects a policy to deploy and incurs a cost that depends on both the chosen policy and current state of the world. The state-evolution dynamics and the costs are allowed to be time-varying, in a possibly adversarial way. In this setting, we study the problem of minimizing policy regret and provide non-constructive upper bounds on the minimax rate for the problem. Our main results provide sufficient conditions for online learnability for this setup with corresponding rates. The rates are characterized by 1) a complexity term capturing the expressiveness of the underlying policy class under the dynamics of state change, and 2) a dynamics stability term measuring the deviation of the instantaneous loss from a certain counterfactual loss. Further, we provide matching lower bounds which show that both the complexity terms are indeed necessary. Our approach provides a unifying analysis that recovers regret bounds for several well studied problems including online learning with memory, online control of linear quadratic regulators, online Markov decision processes, and tracking adversarial targets. In addition, we show how our tools help obtain tight regret bounds for a new problems (with non-linear dynamics and non-convex losses) for which such bounds were not known prior to our work.


Towards Metaheuristics "In the Large"

arXiv.org Artificial Intelligence

Following decades of sustained improvement, metaheuristics are one of the great success stories of optimization research. However, in order for research in metaheuristics to avoid fragmentation and a lack of reproducibility, there is a pressing need for stronger scientific and computational infrastructure to support the development, analysis and comparison of new approaches. We argue that, via principled choice of infrastructure support, the field can pursue a higher level of scientific enquiry. We describe our vision and report on progress, showing how the adoption of common protocols for all metaheuristics can help liberate the potential of the field, easing the exploration of the design space of metaheuristics.


Automated Large-scale Class Scheduling in MiniZinc

arXiv.org Artificial Intelligence

Class Scheduling is a highly constrained task. Educational institutes spend a lot of resources, in the form of time and manual computation, to find a satisficing schedule that fulfills all the requirements. A satisficing class schedule accommodates all the students to all their desired courses at convenient timing. The scheduler also needs to take into account the availability of course teachers on the given slots. With the added limitation of available classrooms, the number of solutions satisfying all constraints in this huge search-space, further decreases. This paper proposes an efficient system to generate class schedules that can fulfill every possible need of a typical university. Though it is primarily a fixed-credit scheduler, it can be adjusted for open-credit systems as well. The model is designed in MiniZinc and solved using various off-the-shelf solvers. The proposed scheduling system can find a balanced schedule for a moderate-sized educational institute in less than a minute.


Solving a few AI problems with Python: Part 1

#artificialintelligence

In this blog we shall discuss about a few problems in artificial intelligence and their python implementations. The problems discussed here appeared as programming assignments in the edX course CS50's Introduction to Artificial Intelligence with Python (HarvardX:CS50 AI). The problem statements are taken from the course itself. Write a program that determines how many "degrees of separation" apart two actors are. According to the Six Degrees of Kevin Bacon game, anyone in the Hollywood film industry can be connected to Kevin Bacon within six steps, where each step consists of finding a film that two actors both starred in.


EECBS: A Bounded-Suboptimal Search for Multi-Agent Path Finding

arXiv.org Artificial Intelligence

Multi-Agent Path Finding (MAPF), i.e., finding collision-free paths for multiple robots, is important for many applications where small runtimes are important, including the kind of automated warehouses operated by Amazon. CBS is a leading two-level search algorithm for solving MAPF optimally. ECBS is a bounded-suboptimal variant of CBS that uses focal search to speed up CBS by sacrificing optimality and instead guaranteeing that the costs of its solution are within a given factor of optimal. In this paper, we study how to decrease its runtime even further using inadmissible heuristics. Motivated by Explicit Estimation Search (EES), we propose Explicit Estimation CBS (EECBS), a new bounded-suboptimal variant of CBS, that uses online learning to inadmissibly estimate the cost of the solution under each high-level node and uses EES to choose which high-level node to expand next. We also investigate recent improvements to CBS and adapt them to EECBS. We find that EECBS with the improvements runs significantly faster than the MAPF algorithms ECBS, BCP-7, and eMDD-SAT on a variety of MAPF instances. We hope that the scalability of EECBS enables wider adoption of MAPF formulations in practical applications.


Using Computer Programs and Search Problems for Teaching Theory of Computation

Communications of the ACM

The theory of computation is one of the crown jewels of the computer science curriculum. It stretches from the discovery of mathematical problems, such as the halting problem, that cannot be solved by computers, to the most celebrated open problem in computer science today: the P vs. NP question. Since the founding of our discipline by Church and Turing in the 1930s, the theory of computation has addressed some of the most fundamental questions about computers: What does it mean to compute the solution to a problem? Which problems can be solved by computers? Which problems can be solved efficiently, in theory and in practice?


Automated Machine Learning (AutoML) Libraries for Python - AnalyticsWeek

#artificialintelligence

AutoML provides tools to automatically discover good machine learning model pipelines for a dataset with very little user intervention. It is ideal for domain experts new to machine learning or machine learning practitioners looking to get good results quickly for a predictive modeling task. Open-source libraries are available for using AutoML methods with popular machine learning libraries in Python, such as the scikit-learn machine learning library. In this tutorial, you will discover how to use top open-source AutoML libraries for scikit-learn in Python. Automated Machine Learning (AutoML) Libraries for Python Photo by Michael Coghlan, some rights reserved.


Automated Machine Learning (AutoML) Libraries for Python

#artificialintelligence

AutoML provides tools to automatically discover good machine learning model pipelines for a dataset with very little user intervention. It is ideal for domain experts new to machine learning or machine learning practitioners looking to get good results quickly for a predictive modeling task. Open-source libraries are available for using AutoML methods with popular machine learning libraries in Python, such as the scikit-learn machine learning library. In this tutorial, you will discover how to use top open-source AutoML libraries for scikit-learn in Python. Automated Machine Learning (AutoML) Libraries for Python Photo by Michael Coghlan, some rights reserved.


Artificial Intelligence

#artificialintelligence

I have done an introduction to Artificial Intelligence (AI) course and I want to share my learning experience. This post covers my notes and summaries of the content of the course. On the early sixties, there was a gathering between several investigators interested on artificial intelligence, neural networks and automats theory as a consequence of the first works made on the field. The problem resolution was based on a general purpose search engine with high cost. To lower that cost, the first search algorithms were developed, like Heuristic Search and Alpha Beta Search.