24 votes
Accepted

What are the tradeoffs between "exact" and Reinforcement Learning methods for solving optimization problems

As far as I understand it, all machine learning approaches used for solving (combinatorial) optimization problems, and in particular reinforcement learning, work as follows: Use a greedy algorithm to ...
user avatar
24 votes
Accepted

Deep Reinforcement Learning for General Purpose Optimization

"General purpose optimization" is quite broad, so I'll take a step back first, to better identifying the motivation of using ML in optimization settings. To keep things simple, I'll consider ...
user avatar
  • 3,283
20 votes

Machine learning and operations research projects

Besides the "obvious" marriage of ML and optimization (namely, use ML to prepare the input for optimization), there can be combinations that make use of the respective strengths: ML is good ...
user avatar
20 votes
Accepted

Using Neural Networks For Solving Optimization Problems

Regarding the paper, it's important to remember that general purpose MIP solvers are meant to be general purpose, hence it's not surprising that they can be improved by tailoring them to the test set, ...
user avatar
19 votes

Machine learning and operations research projects

When you build up your portfolio, you should ask yourself why a specific project is interesting to you (and potentially to a broader audience). What advantage could it have to combine OR and ML, or ...
user avatar
  • 424
19 votes

Machine learning and operations research projects

There are tons of applications of ML for making forecasts in business settings, but in my opinion the more interesting approach is to use ML directly to make decisions—use it for prescriptive, rather ...
user avatar
17 votes
Accepted

Why does the design of heuristics require considerable domain knowledge?

The following is largely opinion/conjecture on my part. Many (though not all) heuristics involve neighborhood search. For that type of heuristic to be effective, you need "neighborhood" to ...
user avatar
  • 29.6k
16 votes
Accepted

What is the connection of Operations Research and Reinforcement Learning?

In the operations research community, many study dynamic programming models and solution approaches. Since many interesting dynamic programming problems attempt to model information uncertainty over ...
user avatar
  • 1,502
16 votes
Accepted

Examples of machine learning applied to operations research?

There are many recent and not so recent papers that use ML to "solve" optimization problems, like Learning Combinatorial Optimization Algorithms over Graphs. A very, very good entry to the subject is ...
user avatar
15 votes

Machine learning and operations research projects

You can have a look at the program of the Deep Learning in Discrete Optimization by William Cook. In addition to the references to material relevant to your question, you can find at the end of the ...
user avatar
14 votes

What are the tradeoffs between "exact" and Reinforcement Learning methods for solving optimization problems

Reinforcement learning is set of the algorithms which are used to solve Markov Decision Processes and its variants, e.g. Partially Observed MDP (POMDP). Most of the problems that we deal with them ...
user avatar
13 votes
Accepted

Estimation of the size of Branch-and-Bound trees using ML

Great question. You might be interested in this paper here: Learning MILP Resolution Outcomes Before Reaching Time-Limit by Martina Fischetti, Andrea Lodi, and Giulia Zarpellon. They don't exactly ...
user avatar
12 votes

Using Neural Networks For Solving Optimization Problems

SCIP is not slow. SCIP's code is roughly as fast as the commercial alternatives. What makes SCIP seem slower to the user is that, by comparison, the commercial solver heuristics (cuts, primal ...
user avatar
11 votes

Examples of machine learning applied to operations research?

Bertsimas and Stellato just put up a new preprint which proposes a method to solve online mixed-integer optimization (MIO) problems at very high speed using machine learning. They benchmark their ...
user avatar
  • 1,313
11 votes

Machine learning and operations research projects

Here two examples that would combine OR and ML swiftly: Suppose you have a math program in which the objective function can only be computed via simulation (very realistic engineering problem). Since ...
user avatar
  • 1,335
11 votes

Best ways to use machine learning / AI as an OR scientist

First, I would argue that the technologies are not necessarily complementary, but can be supplementary. A paper uploaded to Optimization Online just last month discusses the use of machine learning to ...
user avatar
  • 29.6k
10 votes

What is the connection of Operations Research and Reinforcement Learning?

RL (and Machine Learning in general) often use specialized forms of continuous optimization problems that enable one to use elegant solving techniques (e.g. training/learning on the GPU or even ...
user avatar
  • 2,667
9 votes

Machine learning and operations research projects

There are many good answers already, but here are a few viewpoints I have not seen yet. Machine Learning (including deep learning) is nothing but mathematical optimization. Indeed, training a model ...
user avatar
  • 91
9 votes

Which ML algorithms work by solving constrained optimisation problems?

As the borders between statistics and machine learning are diffuse, I take freedom to include statistics. Some links: Non-negative least squares, posts on cross validated. But often restrictions can ...
user avatar
8 votes

Machine learning and operations research projects

This is a post that of my interest. I can give you one such example. I am currently working on an optimization problem, where we have a large LNG gas compressor network (eg. a connected graph with ...
user avatar
8 votes

Machine learning and operations research projects

Machine learning can sometimes be used to create inputs into an optimisation problem. For example, we make a commercial vehicle route optimisation system for dynamic/realtime routing. Travel times ...
user avatar
8 votes

What are the tradeoffs between "exact" and Reinforcement Learning methods for solving optimization problems

A main reason to use Reinforced Learning (RL) is because you don't know the dynamics (update rules) of the system. If you don't know the details of how the system will update, you will not be able to ...
user avatar
8 votes

Queuing Theory with Learning Perspective

Certainly, and to take the problem's structure into account, one could model the queue knowing - or guessing - prior information about the queue's structure and/or parameter distribution and use ...
user avatar
  • 1,577
8 votes

Using Neural Networks For Solving Optimization Problems

Has anyone tested this approach on a real world business problem? If the question is, more generally, "for a practical optimization problem, can ML somehow accelerate the performance of a state-...
user avatar
7 votes

What is the connection of Operations Research and Reinforcement Learning?

Something that I think is becoming more prominent is the use of RL for what would have traditionally been solved using exact solutions. https://medium.com/octavian-ai/finding-shortest-paths-with-...
user avatar
  • 1,059
7 votes

Are there any real-world problems where quadratization helps to solve something that couldn't have been solved without quadratization?

A recent paper by Quantum Computing Inc people is showing experiments on graph partitioning where QUBO approaches lead to better results than the state of the art. Here is the paper: https://arxiv.org/...
user avatar
  • 2,649
7 votes

How would you characterize "optimization data?"

I would call them decision-relevant data, because most optimization problems in practice help people do decisions better, which they already do in a heuristic fashion. This puts the focus on the ...
user avatar
  • 3,477
7 votes

How would you characterize "optimization data?"

I would just call it "planning data". I think it might be easier to convince an administrator that "planning data" needs to be recorded/captured than to sell them on "<...
user avatar
  • 29.6k
6 votes

Machine learning and operations research projects

MDP and ML: The run-time for solving Markov Decision Processes to find the optimal policy is exponentially increased when the problem size is increased. Exact methods for the large problems, most of ...
user avatar
  • 8,290
6 votes

AI gets a lot of attention these days. Does constraint optimization get more attention, too? Why (not)?

This is an interesting question. One way that I'm thinking about this question is to look at how companies are actually using the term AI. I wrote blog post arguing that AI is being used by industry ...
user avatar

Only top scored, non community-wiki answers of a minimum length are eligible