Author name cluster

Matthew Brown

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

NeurIPS Conference 2023 Conference Paper

Module-wise Adaptive Distillation for Multimodality Foundation Models

Chen Liang
Jiahui Yu
Ming-Hsuan Yang
Matthew Brown
Yin Cui
Tuo Zhao
Boqing Gong
Tianyi Zhou

Pre-trained multimodal foundation models have demonstrated remarkable generalizability but pose challenges for deployment due to their large sizes. One effective approach to reducing their sizes is layerwise distillation, wherein small student models are trained to match the hidden representations of large teacher models at each layer. Motivated by our observation that certain architecture components, referred to as modules, contribute more significantly to the student's performance than others, we propose to track the contributions of individual modules by recording the loss decrement after distillation each module and choose the module with a greater contribution to distill more frequently. Such an approach can be naturally formulated as a multi-armed bandit (MAB) problem, where modules and loss decrements are considered as arms and rewards, respectively. We then develop a modified-Thompson sampling algorithm named OPTIMA to address the nonstationarity of module contributions resulting from model updating. Specifically, we leverage the observed contributions in recent history to estimate the changing contribution of each module and select modules based on these estimations to maximize the cumulative contribution. We evaluate the effectiveness of OPTIMA through distillation experiments on various multimodal understanding and image captioning tasks, using the CoCa-Large model \citep{yu2022coca} as the teacher model.

PDF Details

AAAI Conference 2016 Conference Paper

One Size Does Not Fit All: A Game-Theoretic Approach for Dynamically and Effectively Screening for Threats

Matthew Brown
Arunesh Sinha
Aaron Schlenker
Milind Tambe

An effective way of preventing attacks in secure areas is to screen for threats (people, objects) before entry, e. g. , screening of airport passengers. However, screening every entity at the same level may be both ineffective and undesirable. The challenge then is to ﬁnd a dynamic approach for randomized screening, allowing for more effective use of limited screening resources, leading to improved security. We address this challenge with the following contributions: (1) a threat screening game (TSG) model for general screening domains; (2) an NP-hardness proof for computing the optimal strategy of TSGs; (3) a scheme for decomposing TSGs into subgames to improve scalability; (4) a novel algorithm that exploits a compact game representation to efﬁciently solve TSGs, providing the optimal solution under certain conditions; and (5) an empirical comparison of our proposed algorithm against the current state-of-the-art optimal approach for large-scale game-theoretic resource allocation problems.

PDF Details

AAMAS Conference 2016 Conference Paper

SPECTRE: A Game Theoretic Framework for Preventing Collusion in Security Games (Demonstration)

Shahrzad Gholami
Bryan Wilder
Matthew Brown
Arunesh Sinha
Nicole Sintov
Milind Tambe

Several models have been proposed for Stackelberg security games (SSGs) and protection against perfectly rational and bounded rational adversaries; however, none of these existing models addressed the destructive cooperation mechanism between adversaries. SPECTRE (Strategic Patrol planner to Extinguish Collusive ThREats) takes into account the synergistic destructive collusion among two groups of adversaries in security games. This framework is designed for the purpose of efficient patrol scheduling for security agents in security games in presence of collusion and is mainly build up on game theoretic approaches, optimization techniques, machine learning methods and theories for human decision making under risk. The major advantage of SPECTRE is involving real world data from human subject experiments with participants on Amazon Mechanical Turk (AMT).

PDF

RLDM Conference 2015 Conference Abstract

Valuation systems in risky decisions from description and experience

Christopher Madan
Elliot Ludvig
Matthew Brown
Marcia Spetch

People’s risk preferences differ when making choices based on described probabilities versus those based on information learned through experience. When decisions are made from description, people are more risk averse for gains than losses (reflection effect). However, when decisions are made from experience, people are sometimes more risk seeking for gains than losses, especially with the possibility of extreme outcomes. Here we investigated the relationship between these decision-making processes further in two experiments: (1) in a large sample, examining the correlations between risk preferences in decisions from description and experience, and (2) in an fMRI study, examining differential brain activations when making decisions from description vs. experience. In Experiment 1, we found that these two risk preference biases were related—participants who exhibited a stronger reflection effect demonstrated less of a bias due to extreme outcomes. In Experiment 2, we found that prefrontal regions were more engaged in decisions from description, while regions within the temporal lobe were engaged to a greater degree in decisions from experience. These results suggest that risky choice may be best understood as reflecting the output of two valuation processes—a simple memory-driven kernel and a control process that evaluates stated probabilities.

PDF Details

ICRA Conference 2013 Conference Paper

A nonlinear feedback controller for aerial self-righting by a tailed robot

Evan Chang-Siu
Thomas Libby
Matthew Brown
Robert J. Full
Masayoshi Tomizuka

In this work, we propose a control scheme for attitude control of a falling, two link active tailed robot with only two degrees of freedom of actuation. We derive a simplified expression for the robot's angular momentum and invert this expression to solve for the shape velocities that drive the body's angular momentum to a desired value. By choosing a body angular velocity vector parallel to the axis of error rotation, the controller steers the robot towards its desired orientation. The proposed scheme is accomplished through feedback laws as opposed to feedforward trajectory generation, is fairly robust to model uncertainties, and is simple enough to implement on a miniature microcontroller. We verify our approach by implementing the controller on a small (175 g) robot platform, enabling rapid maneuvers approaching the spectacular capability of animals.

Details

JAAMAS Journal 2012 Journal Article

An extended study on multi-objective security games

Matthew Brown
Bo An
Milind Tambe

Abstract The burgeoning area of security games has focused on real-world domains where security agencies protect critical infrastructure from a diverse set of adaptive adversaries. In such domains, decision makers have multiple competing objectives they must consider which may take different forms that are not readily comparable including safety, cost, and public perception. Thus, it can be difficult to know how to weigh the different objectives when deciding on a security strategy. To address the challenges of these domains, we propose a fundamentally different solution concept, multi-objective security games (MOSGs). Instead of a single optimal solution, MOSGs have a set of Pareto optimal (non-dominated) solutions referred to as the Pareto frontier, which can be generated by solving a sequence of constrained single-objective optimization problems (CSOPs). The Pareto frontier allows the decision maker to analyze the tradeoffs that exist between the multiple objectives. Our contributions include: (i) an algorithm, Iterative-ε-Constraints, , for generating the sequence of CSOPs; (ii) an exact approach for solving an mixed-integer linear program (MILP) formulation of a CSOP; (iii) heuristics that achieve speed up by exploiting the structure of security games to further constrain the MILP; (iv) an approximate approach for solving a CSOP built off those same heuristics, increasing the scalability of our approach with quality guarantees. Additional contributions of this paper include proofs on the level of approximation, detailed experimental evaluation of the proposed approaches and heuristics, as well as a discussion on techniques for visualizing the Pareto frontier.

Details DOI

AAMAS Conference 2012 Conference Paper

Multi-Objective Optimization for Security Games

Matthew Brown
Bo An
Christopher Kiekintveld
Fernando Ord
oacute;
ntilde; ez
Milind Tambe

The burgeoning area of security games has focused on real-world domains where security agencies protect critical infrastructure from a diverse set of adaptive adversaries. There are security domains where the payoffs for preventing the different types of adversaries may take different forms (seized money, reduced crime, saved lives, etc) which are not readily comparable. Thus, it can be difficult to know how to weigh the different payoffs when deciding on a security strategy. To address the challenges of these domains, we propose a fundamentally different solution concept, multi-objective security games (MOSG), which combines security games and multi-objective optimization. Instead of a single optimal solution, MOSGs have a set of Pareto optimal (non-dominated) solutions referred to as the Pareto frontier. The Pareto frontier can be generated by solving a sequence of constrained single-objective optimization problems (CSOP), where one objective is selected to be maximized while lower bounds are specified for the other objectives. Our contributions include: (i) an algorithm, Iterative $\epsilon$-Constraints, for generating the sequence of CSOPs; (ii) an exact approach for solving an MILP formulation of a CSOP (which also applies to multi-objective optimization in more general Stackelberg games); (iii) heuristics that achieve speedup by exploiting the structure of security games to further constrain a CSOP; (iv) an approximate approach for solving an algorithmic formulation of a CSOP, increasing the scalability of our approach with quality guarantees. Additional contributions of this paper include proofs on the level of approximation and detailed experimental evaluation of the proposed approaches.

PDF

AAMAS Conference 2011 Conference Paper

ESCAPES - Evacuation Simulation with Children, Authorities, Parents, Emotions, and Social comparison

Jason Tsai
Natalie Fridman
Emma Bowring
Matthew Brown
Shira Epstein
Gal A. Kaminka
Stacy Marsella
Andrew Ogden

In creating an evacuation simulation for training and planning, realistic agents that reproduce known phenomenon are required. Evacuation simulation in the airport domain requires additional features beyond most simulations, including the unique behaviors of first-time visitors who have incomplete knowledge of the area and families that do not necessarily adhere to often-assumed pedestrian behaviors. Evacuation simulations not customized for the airport domain do not incorporate the factors important to it, leading to inaccuracies when applied to it. In this paper, we describe ESCAPES, a multiagent evacuation simulation tool that incorporates four key features: (i) different agent types; (ii) emotional interactions; (iii) informational interactions; (iv) behavioral interactions. Our simulator reproduces phenomena observed in existing studies on evacuation scenarios and the features we incorporate substantially impact escape time. We use ESCAPES to model the International Terminal at Los Angeles International Airport (LAX) and receive high praise from security officials.

PDF