Parbhoo S, Joshi S, Doshi-Velez F.
Learning-to-defer for sequential medical decision-making under uncertainty. Proceedings of the International Conference on Machine Learning: Workshop on Neglected Assumptions in Causal Inference (ICML). 2021.
Publisher's VersionAbstractLearning-to-defer is a framework to automatically defer decision-making to a human expert when ML-based decisions are deemed unreliable. Existing learning-to-defer frameworks are not designed for sequential settings. That is, they defer at every instance independently, based on immediate predictions, while ignoring the potential long-term impact of these interventions. As a result, existing frameworks are myopic. Further, they do not defer adaptively, which is crucial when human interventions are costly. In this work, we propose Sequential Learning-to-Defer (SLTD), a framework for learning-to-defer to a domain expert in sequential decision-making settings. Contrary to existing literature, we pose the problem of learning-to-defer as model-based reinforcement learning (RL) to i) account for long-term consequences of ML-based actions using RL and ii) adaptively defer based on the dynamics (model-based). Our proposed framework determines whether to defer (at each time step) by quantifying whether a deferral now will improve the value compared to delaying deferral to the next time step. To quantify the improvement, we account for potential future deferrals. As a result, we learn a pre-emptive deferral policy (i.e. a policy that defers early if using the ML-based policy could worsen long-term outcomes). Our deferral policy is adaptive to the non-stationarity in the dynamics. We demonstrate that adaptive deferral via SLTD provides an improved trade-off between long-term outcomes and deferral frequency on synthetic, semi-synthetic, and real-world data with non-stationary dynamics. Finally, we interpret the deferral decision by decomposing the propagated (long-term) uncertainty around the outcome, to justify the deferral decision.
2109.06312.pdf Zhang H, Dullerud N, Seyyed-Kalantari L, Morris Q, Joshi S, Ghassemi M.
An Empirical Framework for Domain Generalization in Clinical Settings. Conference for Health, Inference, and Learning (CHIL) 2021. 2021.
Publisher's VersionAbstract Clinical machine learning models experience significantly degraded performance in datasets not seen during training, e.g., new hospitals or populations. Recent developments in domain generalization offer a promising solution to this problem by creating models that learn invariances across environments. In this work, we benchmark the performance of eight domain generalization methods on multi-site clinical time series and medical imaging data. We introduce a framework to induce synthetic but realistic domain shifts and sampling bias to stress-test these methods over existing non-healthcare benchmarks. We find that current domain generalization methods do not consistently achieve significant gains in out-of-distribution performance over empirical risk minimization on real-world medical imaging data, in line with prior work on general imaging datasets. However, a subset of realistic induced-shift scenarios in clinical time series data do exhibit limited performance gains. We characterize these scenarios in detail, and recommend best practices for domain generalization in the clinical setting.
2103.11163.pdf Jia F, Mate A, Li Z, Jabbari S, Chakraborty M, Tambe M, Wellman M, Vorobeychik Y.
A Game-Theoretic Approach for Hierarchical Policy-Making. nd International (Virtual) Workshop on Autonomous Agents for Social Good (AASG 2021). 2021.
Publisher's VersionAbstract
We present the design and analysis of a multi-level game-theoretic model of hierarchical policy-making, inspired by policy responses to the COVID-19 pandemic. Our model captures the potentially mismatched priorities among a hierarchy of policy-makers (e.g., federal, state, and local governments) with respect to two main cost components that have opposite dependence on the policy strength, such as post-intervention infection rates and the cost of policy implementation. Our model further includes a crucial third fac- tor in decisions: a cost of non-compliance with the policy-maker immediately above in the hierarchy, such as non-compliance of state with federal policies. Our first contribution is a closed-form approximation of a recently published agent-based model to com- pute the number of infections for any implemented policy. Second, we present a novel equilibrium selection criterion that addresses common issues with equilibrium multiplicity in our setting. Third, we propose a hierarchical algorithm based on best response dynamics for computing an approximate equilibrium of the hierarchical policy-making game consistent with our solution concept. Finally, we present an empirical investigation of equilibrium policy strategies in this game as a function of game parameters, such as the degree of centralization and disagreements about policy priorities among the agents, the extent of free riding as well as fairness in the distribution of costs.
aasg_2021_paper_9.pdf Ou H-C, Chen H, Jabbari S, Tambe M.
Active Screening for Recurrent Diseases: A Reinforcement Learning Approach. 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS). 2021.
AbstractActive screening is a common approach in controlling the spread of recurring infectious diseases such as tuberculosis and influenza. In this approach, health workers periodically select a subset of population for screening. However, given the limited number of health workers, only a small subset of the population can be visited in any given time period. Given the recurrent nature of the disease and rapid spreading, the goal is to minimize the number of infections over a long time horizon. Active screening can be formalized as a sequential combinatorial optimization over the network of people and their connections. The main computational challenges in this formalization arise from i) the combinatorial nature of the problem, ii) the need of sequential planning and iii) the uncertainties in the infectiousness states of the population.
ou_et_al._-_2021_-_active_screening_for_recurrent_diseases_a_reinfor.pdf Killian JA, Perrault A, Tambe M.
Beyond “To Act or Not to Act”: Fast Lagrangian Approaches to General Multi-Action Restless Bandits. IJCAI 2021 Workshop on AI for Social Good. 2021.
AbstractWe present a new algorithm and theoretical results for solving Multi-action Multi-armed Restless Bandits, an important but insufficiently studied generalization of traditional Multi-armed Restless Bandits (MARBs). Multi-action MARBs are capable of handling critical problem complexities often present in AI4SG domains like anti-poaching and healthcare, but that traditional MARBs fail to capture. Limited previous work on Multi-action MARBs has only been specialized to sub-problems. Here we derive BLam, an algorithm for general Multi-action MARBs using Lagrangian relaxation techniques and convexity to quickly converge to good policies via bound optimization. We also provide experimental results comparing BLam to baselines on a simulated distributions motivated by a real-world community health intervention task, achieving up to five-times speedups over more general methods without sacrificing performance.
Beyond “To Act or Not to Act”: Fast Lagrangian Approaches to General Multi-Action Restless Bandits