Related papers: Designing with Static Capabilities and Effects: Us…
In decentralized stochastic control (or stochastic team theory) and game theory, if there is a pre-defined order in a system in which agents act, the system is called \textit{sequential}, otherwise it is non-sequential. Much of the…
The success of vision transformers is widely attributed to the expressive power of their dynamically parameterized multi-head self-attention mechanism. We examine the impact of substituting the dynamic parameterized key with a static key…
Flat optics is now judged by more than a strong simulation or a single laboratory demonstration. To reach release, a device must survive a chain of handoffs: requirements, model selection, verification, layout release, fabrication,…
In traditional machine teaching, a teacher wants to teach a concept to a learner, by means of a finite set of examples, the witness set. But concepts can have many equivalent representations. This redundancy strongly affects the search…
Iterative imperative programs can be considered as infinite-state systems computing over possibly unbounded domains. Studying reachability in these systems is challenging as it requires to deal with an infinite number of states with…
Compact representations of objects is a common concept in computer science. Automated planning can be viewed as a case of this concept: a planning instance is a compact implicit representation of a graph and the problem is to find a path (a…
This paper considers how to classify the effects of interventions in causal models for outcomes and exposures observed over time. First, we demonstrate the limitations of the most common uses of potential outcomes and causal directed…
In real-world search, recommendation, and advertising systems, the multi-stage ranking architecture is commonly adopted. Such architecture usually consists of matching, pre-ranking, ranking, and re-ranking stages. In the pre-ranking stage,…
Detecting feature interactions is imperative for accurately predicting performance of highly-configurable systems. State-of-the-art performance prediction techniques rely on supervised machine learning for detecting feature interactions,…
A fundamental result in mechanism design theory, the so-called revelation principle, asserts that for many questions concerning the existence of mechanisms with a given outcome one can restrict attention to truthful direct…
We show that there may exist an inherent tension between the goal of adversarial robustness and that of standard generalization. Specifically, training robust models may not only be more resource-consuming, but also lead to a reduction of…
In this paper, we derive a number of inequalities which express power-efficiency trade-offs that hold generally for thermodynamic machines operating in non-equilibrium stationary states. One of these inequalities concerns the output power,…
Classical semantics assumes that one can model reference, predication and quantification with respect to a fixed domain of precise referent objects. Non-logical terms and quantification are then interpreted directly in terms of elements and…
Transfer in reinforcement learning refers to the notion that generalization should occur not only within a task but also across tasks. We propose a transfer framework for the scenario where the reward function changes between tasks but the…
A striking limitation of human cognition is our inability to execute some tasks simultaneously. Recent work suggests that such limitations can arise from a fundamental tradeoff in network architectures that is driven by the sharing of…
Reinforcement learning and classical planning are typically seen as two distinct problems, with differing formulations necessitating different solutions. Yet, when humans are given a task, regardless of the way it is specified, they can…
Decision-making AI agents are often faced with two important challenges: the depth of the planning horizon, and the branching factor due to having many choices. Hierarchical reinforcement learning methods aim to solve the first problem, by…
Actor systems are a flexible model of concurrent and distributed programming, which are efficiently implementable, and avoid many classic concurrency bugs by construction. However actor systems must still deal with the challenge of messages…
Writing parallel codes is difficult and exhibits a fundamental trade-off between abstraction and performance. The high level language abstractions designed to simplify the complexities of parallelism make certain assumptions that impacts…
Classic market design theory is rooted in static models where all participants trade simultaneously. In contrast, modern platform-mediated digital markets are fundamentally dynamic, defined by the asynchronous and stochastic arrival of…