24/7 Space News
Automating the math for decision-making under uncertainty
ADEV automates the math for maximizing the expected value of actions in an uncertain world.
Automating the math for decision-making under uncertainty
by Rachel Paiste | MIT CSAIL
Boston MA (SPX) Feb 08, 2023

One reason deep learning exploded over the last decade was the availability of programming languages that could automate the math - college-level calculus - that is needed to train each new model. Neural networks are trained by tuning their parameters to try to maximize a score that can be rapidly calculated for training data.

The equations used to adjust the parameters in each tuning step used to be derived painstakingly by hand. Deep learning platforms use a method called automatic differentiation to calculate the adjustments automatically. This allowed researchers to rapidly explore a huge space of models, and find the ones that really worked, without needing to know the underlying math.

But what about problems like climate modeling, or financial planning, where the underlying scenarios are fundamentally uncertain? For these problems, calculus alone is not enough - you also need probability theory. The "score" is no longer just a deterministic function of the parameters.

Instead, it's defined by a stochastic model that makes random choices to model unknowns. If you try to use deep learning platforms on these problems, they can easily give the wrong answer. To fix this problem, MIT researchers developed ADEV, which extends automatic differentiation to handle models that make random choices. This brings the benefits of AI programming to a much broader class of problems, enabling rapid experimentation with models that can reason about uncertain situations.

Lead author and MIT electrical engineering and computer science PhD student Alex Lew says he hopes people will be less wary of using probabilistic models now that there's a tool to automatically differentiate them.

"The need to derive low-variance, unbiased gradient estimators by hand can lead to a perception that probabilistic models are trickier or more finicky to work with than deterministic ones. But probability is an incredibly useful tool for modeling the world. My hope is that by providing a framework for building these estimators automatically, ADEV will make it more attractive to experiment with probabilistic models, possibly enabling new discoveries and advances in AI and beyond."

Sasa Misailovic, an associate professor at the University of Illinois at Urbana-Champaign who was not involved in this research, adds: "As the probabilistic programming paradigm is emerging to solve various problems in science and engineering, questions arise on how we can make efficient software implementations built on solid mathematical principles.

ADEV presents such a foundation for modular and compositional probabilistic inference with derivatives. ADEV brings the benefits of probabilistic programming - automated math and more scalable inference algorithms - to a much broader range of problems where the goal is not just to infer what is probably true but to decide what action to take next."

In addition to climate modeling and financial modeling, ADEV could also be used for operations research - for example, simulating customer queues for call centers to minimize expected wait times, by simulating the wait processes and evaluating the quality of outcomes - or for tuning the algorithm that a robot uses to grasp physical objects. Co-author Mathieu Huot says he's excited to see ADEV "used as a design space for novel low-variance estimators, a key challenge in probabilistic computations."

The research, awarded the SIGPLAN Distinguished Paper award at POPL 2023, is co-authored by Vikash Mansighka, who leads MIT's Probabilistic Computing Project in the Department of Brain and Cognitive Sciences and the Computer Science and Artificial Intelligence Laboratory, and helps lead the MIT Quest for Intelligence, as well as Mathieu Huot and Sam Staton, both at Oxford University.

Huot adds, "ADEV gives a unified framework for reasoning about the ubiquitous problem of estimating gradients unbiasedly, in a clean, elegant and compositional way." The research was supported by the National Science Foundation, the DARPA Machine Common Sense program, and a philanthropic gift from the Siegel Family Foundation.

"Many of our most controversial decisions - from climate policy to the tax code - boil down to decision-making under uncertainty. ADEV makes it easier to experiment with new ways to solve these problems, by automating some of the hardest math," says Mansinghka. "For any problem that we can model using a probabilistic program, we have new, automated ways to tune the parameters to try to create outcomes that we want, and avoid outcomes that we don't."

Research Report:ADEV: Sound Automatic Differentiation of Expected Values of Probabilistic Programs

Related Links
Computer Science and Artificial Intelligence Laboratory (CSAIL)
Space Technology News - Applications and Research

Subscribe Free To Our Daily Newsletters

The following news reports may link to other Space Media Network websites.
Matrix multiplications at the speed of light
Washington DC (SPX) Feb 03, 2023
"All things are numbers," avowed Pythagoras. Today, 25 centuries later, algebra and mathematics are everywhere in our lives, whether we see them or not. The Cambrian-like explosion of artificial intelligence (AI) brought numbers even closer to us all, since technological evolution allows for parallel processing of a vast amounts of operations. Progressively, operations between scalars (numbers) were parallelized into operations between vectors and, subsequently, matrices. Multiplication between ma ... read more

NASA's Aerospace Safety Advisory Panel releases 2022 Annual Report

Design a spacesuit for ESA

Setting sail for safer space

NASA names first person of Hispanic heritage as chief astronaut

SpaceX to test-fire all 33 Starship booster engines Thursday

Launches of Busek Thrusters push OneWeb constellation towards completion

SpaceX launches Hispasat's Amazonas Nexus communication satellite

Poland's SatRev signs on for future Virgin Orbit flights

Preparing to drill Dinira: Sols 3737-3738

Mars Helicopter at Three Forks

Searching for a Drill Site Near Encanto: Sols 3735-3736

Enchanting Encanto Calls: Sols 3732-3734

China's Deep Space Exploration Lab eyes top global talents

Chinese astronauts send Spring Festival greetings from space station

China to launch 200-plus spacecraft in 2023

China's space industry hits new heights

OneWeb and Kazakhstan National Railways to work together

Sidus Space closes public offering

Iridium GO exec redefines personal off-the-grid connectivity

ATLAS works with AWS to advance federated network and expand ground station coverage

High efficiency mid- and long-wave optical parametric oscillator pump source and its applications

Automating the math for decision-making under uncertainty

Understanding laser accelerated electron radiation through terahertz emissions

Turkey's once mighty developers under fire after quake

Researchers focus AI on finding exoplanets

A nearby potentially habitable Earth-mass exoplanet

Two nearby exoplanets might be habitable

Will machine learning help us find extraterrestrial life

SwRI models explain canyons on Pluto moon

NASA's Juno Team assessing camera after 48th flyby of Jupiter

Webb spies Chariklo ring system with high-precision technique

Europe's JUICE spacecraft ready to explore Jupiter's icy moons

Subscribe Free To Our Daily Newsletters


The content herein, unless otherwise known to be public domain, are Copyright 1995-2023 - Space Media Network. All websites are published in Australia and are solely subject to Australian law and governed by Fair Use principals for news reporting and research purposes. AFP, UPI and IANS news wire stories are copyright Agence France-Presse, United Press International and Indo-Asia News Service. ESA news reports are copyright European Space Agency. All NASA sourced material is public domain. Additional copyrights may apply in whole or part to other bona fide parties. All articles labeled "by Staff Writers" include reports supplied to Space Media Network by industry news wires, PR agencies, corporate press officers and the like. Such articles are individually curated and edited by Space Media Network staff on the basis of the report's information value to our industry and professional readership. Advertising does not imply endorsement, agreement or approval of any opinions, statements or information provided by Space Media Network on any Web page published or hosted by Space Media Network. General Data Protection Regulation (GDPR) Statement Our advertisers use various cookies and the like to deliver the best ad banner available at one time. All network advertising suppliers have GDPR policies (Legitimate Interest) that conform with EU regulations for data collection. By using our websites you consent to cookie based advertising. If you do not agree with this then you must stop using the websites from May 25, 2018. Privacy Statement. Additional information can be found here at About Us.