Author name cluster

Marc van Zee

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.

7 papers

2 author rows

JMLR Journal 2023 Journal Article

Scaling Up Models and Data with t5x and seqio

Adam Roberts
Hyung Won Chung
Gaurav Mishra
Anselm Levskaya
James Bradbury
Daniel Andor
Sharan Narang
Brian Lester

Scaling up training datasets and model parameters have benefited neural network-based language models, but also present challenges like distributed compute, input data bottlenecks and reproducibility of results. We introduce two simple and scalable software libraries that simplify these issues: t5x enables training large language models at scale, while seqio enables reproducible input and evaluation pipelines. These open-source libraries have been used to train models with hundreds of billions of parameters on multi-terabyte datasets. Configurations and instructions for T5-like and GPT-like models are also provided. The libraries can be found at https://github.com/google-research/t5x and https://github.com/google/seqio. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2023. ( edit, beta )

PDF Details

AIJ Journal 2020 Journal Article

Intention as commitment toward time

Marc van Zee
Dragan Doder
Leendert van der Torre
Mehdi Dastani
Thomas Icard
Eric Pacuit

In this paper we address the interplay among intention, time, and belief in dynamic environments. The first contribution is a logic for reasoning about intention, time and belief, in which assumptions of intentions are represented by preconditions of intended actions. Intentions and beliefs are coherent as long as these assumptions are not violated, i. e. as long as intended actions can be performed such that their preconditions hold as well. The second contribution is the formalization of what-if scenarios: what happens with intentions and beliefs if a new (possibly conflicting) intention is adopted, or a new fact is learned? An agent is committed to its intended actions as long as its belief-intention database is coherent. We conceptualize intention as commitment toward time and we develop AGM-based postulates for the iterated revision of belief-intention databases, and we prove a Katsuno-Mendelzon-style representation theorem.

Details DOI

ICLR Conference 2020 Conference Paper

Measuring Compositional Generalization: A Comprehensive Method on Realistic Data

Daniel Keysers
Nathanael Schärli
Nathan Scales
Hylke Buisman
Daniel Furrer
Sergii Kashubin
Nikola Momchev
Danila Sinopalnikov

State-of-the-art machine learning methods exhibit limited compositional generalization. At the same time, there is a lack of realistic benchmarks that comprehensively measure this ability, which makes it challenging to find and evaluate improvements. We introduce a novel method to systematically construct such benchmarks by maximizing compound divergence while guaranteeing a small atom divergence between train and test sets, and we quantitatively compare this method to other approaches for creating compositional generalization benchmarks. We present a large and realistic natural language question answering dataset that is constructed according to this method, and we use it to analyze the compositional generalization ability of three machine learning architectures. We find that they fail to generalize compositionally and that there is a surprisingly strong negative correlation between compound divergence and accuracy. We also demonstrate how our method can be used to create new compositionality benchmarks on top of the existing SCAN dataset, which confirms these findings.

Details

ECAI Conference 2016 Conference Paper

AGM-Style Revision of Beliefs and Intentions

Marc van Zee
Dragan Doder

We introduce a logic for temporal beliefs and intentions based on Shoham's database perspective and we formalize his coherence conditions on beliefs and intentions. In order to do this we separate strong beliefs from weak beliefs. Strong beliefs are independent from intentions, while weak beliefs are obtained by adding intentions to strong beliefs and everything that follows from that. We provide AGM-style postulates for the revision of strong beliefs and intentions: strong belief revision may trigger intention revision, but intention revision may only trigger revision of weak beliefs. After revision, the strong beliefs are coherent with the intentions. We show in a representation theorem that a revision operator satisfying our postulates can be represented by a pre-order on interpretations of the beliefs, together with a selection function for the intentions.

Details

IJCAI Conference 2015 Conference Paper

AGM Revision of Beliefs about Action and Time

Marc van Zee
Dragan Doder
Mehdi Dastani
Leendert van der Torre

The AGM theory of belief revision is based on propositional belief sets. In this paper we develop a logic for revision of temporal belief bases, containing expressions about temporal propositions (tomorrow it will rain), possibility (it may rain tomorrow), actions (the robot enters the room) and preand post-conditions of these actions. We prove the Katsuno-Mendelzon and the Darwiche-Pearl representation theorems by restricting the logic to formulas representing beliefs up to certain time. We illustrate our belief change model through several examples.

PDF Details

IJCAI Conference 2015 Conference Paper

Rational Architecture = Architecture from a Recommender Perspective

Marc van Zee

An Enterprise Architecture (EA) provides a holistic view of an enterprise. In creating or changing an EA, multiple decisions have to be made, which are based on assumptions about the situation at hand. In this thesis, we develop a framework for reasoning about changing decisions and assumptions, based on logical theories of intentions. This framework serves as the underlying formalism for a recommender system for EA decision making.

PDF Details

AAAI Conference 2013 Conference Paper

Multi-Cycle Query Caching in Agent Programming

Natasha Alechina
Tristan Behrens
Mehdi Dastani
Koen Hindriks
Jomi Hubner
Brian Logan
Hai Nguyen
Marc van Zee

In many logic-based BDI agent programming languages, plan selection involves inferencing over some underlying knowledge representation. While context-sensitive plan selection facilitates the development of flexible, declarative programs, the overhead of evaluating repeated queries to the agent’s beliefs and goals can result in poor run time performance. In this paper we present an approach to multi-cycle query caching for logic-based BDI agent programming languages. We extend the abstract performance model presented in (Alechina et al. 2012) to quantify the costs and benefits of caching query results over multiple deliberation cycles. We also present results of experiments with prototype implementations of both single- and multi-cycle caching in three logic-based BDI agent platforms, which demonstrate that significant performance improvements are achievable in practice.

PDF Details