Algorithm may be applied to a broad range of complicated problems.
To work with computational models is to work in a world of unknowns: Models that simulate complex physical processes — from Earth’s changing climate to the performance of hypersonic combustion engines — are staggeringly complex, sometimes incorporating hundreds of parameters, each of which describes a piece of the larger process.
Parameters are often question marks within their models, their contributions to the whole largely unknown. To estimate the value of each unknown parameter requires plugging in hundreds, if not thousands, of values, and running the model each time to narrow in on an accurate value — a computation that can take days, and sometimes weeks.
Now MIT researchers have developed a new algorithm that vastly reduces the computation of virtually any computational model. The algorithm may be thought of as a shrinking bull’s-eye that, over several runs of a model, and in combination with some relevant data points, incrementally narrows in on its target: a probability distribution of values for each unknown parameter.
With this method, the researchers were able to arrive at the same answer as a classic computational approaches, but 200 times faster.
Youssef Marzouk, an associate professor of aeronautics and astronautics, says the algorithm is versatile enough to apply to a wide range of computationally intensive problems.
“We’re somewhat flexible about the particular application,” Marzouk says. “These models exist in a vast array of fields, from engineering and geophysics to subsurface modeling, very often with unknown parameters. We want to treat the model as a black box and say, ‘Can we accelerate this process in some way?’ That’s what our algorithm does.”
Marzouk and his colleagues — recent PhD graduate Patrick Conrad, Natesh Pillai from Harvard University, and Aaron Smith from the University of Ottawa — have published their findings this week in the Journal of the American Statistical Association.
Modeling “Monopoly”
In working with complicated models involving multiple unknown parameters, computer scientists typically employ a technique called Markov chain Monte Carlo (MCMC) analysis — a statistical sampling method that is often explained in the context of the board game “Monopoly.”
To plan out a monopoly, you want to know which properties players land on most often — essentially, an unknown parameter. Each space on the board has a probability of being landed on, determined by the rules of the game, the positions of each player, and the roll of two dice. To determine the probability distribution on the board — the range of chances each space has of being landed on — you could roll the die hundreds of times.
If you roll the die enough times, you can get a pretty good idea of where players will most likely land. This, essentially, is how an MCMC analysis works: by running a model over and over, with different inputs, to determine a probability distribution for one unknown parameter. For more complicated models involving multiple unknowns, the same method could take days to weeks to compute an answer.
Shrinking bull’s-eye
With their new algorithm, Marzouk and his colleagues aim to significantly speed up the conventional sampling process.
“What our algorithm does is short-circuits this model and puts in an approximate model,” Marzouk explains. “It may be orders of magnitude cheaper to evaluate.”
The algorithm can be applied to any complex model to quickly determine the probability distribution, or the most likely values, for an unknown parameter. Like the MCMC analysis, the algorithm runs a given model with various inputs — though sparingly, as this process can be quite time-consuming. To speed the process up, the algorithm also uses relevant data to help narrow in on approximate values for unknown parameters.
Read more: Shrinking bull’s-eye algorithm speeds up complex modeling from days to hours
The Latest on: Shrinking bull’s-eye algorithm
[google_news title=”” keyword=”Shrinking bull’s-eye algorithm” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Shrinking bull’s-eye algorithm
- Correspondents: Bull’s Eyeon March 20, 2024 at 11:13 pm
DOMINICAN REGIME NEAR COLLAPSE.screamed a New York World-Telegram headline last week. “The governmentof President Juan Bosch,” wrote Hal Hendrix, 41, the Telly’s new LatinAmerican ...
- Algorithm Not for Saleon March 14, 2024 at 2:29 am
What could possibly go wrong? And, interestingly, it's not just ByteDance's hesitation to part with its algorithm, so much as it is China itself that has purportedly "issued regulations that ...
- Bitcoin paints bull’s-eye on $100,000 before halving. Here’s what’s driving this crypto rally.on March 9, 2024 at 6:27 pm
Some cryptocurrency bulls are now eyeing $100,000 as bitcoin’s next level, after the leading crypto asset on Friday briefly topped $70,000 for the first time in its history. Mark Connors ...
- Bitcoin paints bull’s-eye on $100,000 before halving. Here’s what’s driving this crypto rally.on March 8, 2024 at 4:00 pm
Some cryptocurrency bulls are now eyeing $100,000 as bitcoin ... Halving is a mechanism written into the Bitcoin blockchain’s algorithm to control the coin’s supply, which has a cap of ...
- Bitcoin bulls eye $100,000 as the next level before its halving. Here’s what’s driving the crypto’s rally.on March 8, 2024 at 1:52 pm
Some crypto bulls are now eyeing $100,000 as bitcoin ... Halving is a mechanism written into the Bitcoin blockchain’s algorithm to control the coin’s supply, which has a cap of 21 million.
- Severe thunderstorms headed to the Southon March 6, 2024 at 11:02 pm
Cities in the bull's-eye Thursday include Fort Worth, Waco and Oklahoma City. More rain and thunderstorms are expected across the South, from Texas to Florida, over the next three days.
- The Press: Bull’s-Eyeon February 27, 2024 at 3:00 pm
Explanation of this astonishing bull’s-eye: LIFE’S editors, knowing no more than any other laymen about where the invasion would strike, had simply chosen what seemed to them a likely spot.
- How we almost ended up with a bull's-eye bar codeon January 11, 2024 at 9:55 am
When I began combing through the archive of bar code history at Stony Brook University, I realized just how close we came to a world where we scan bull's-eye or Sun symbols to buy our groceries.
- Best Shooting Range: Bull's Eyeon March 30, 2022 at 1:39 am
Bull's Eye, the only indoor shooting range in the city of St. Louis, rents pistols, rifles and one brand-new full-auto, an Uzi, till 9 p.m. Tuesday through Friday, and from 10 a.m. to 6 p.m. Saturday.
- What To Watch For In The Night Sky This Week: January 18-24, 2021on January 17, 2021 at 7:00 pm
then try a star-hop from Orion to a stunning star cluster via the “bull’s eye” star—Aldebaran. With a Last Quarter Moon on Wednesday, the night skies will begin to brighten, making star ...
via Bing News