Questions tagged [optimization]

For questions about implementing and improving optimization algorithms used in creating AI programs, or optimization in general.

Filter by
Sorted by
Tagged with
10
votes
2answers
254 views

Can artificial intelligence be thought of as optimization?

In this video an expert says, "One way of thinking about what intelligence is [specifically with regard to artificial intelligence], is as an optimization process." Can intelligence always be thought ...
10
votes
1answer
3k views

Loss jumps abruptly when I decay the learning rate with Adam optimizer in PyTorch

I'm training an auto-encoder network with Adam optimizer (with amsgrad=True) and ...
9
votes
2answers
6k views

What are the limitations of the hill climbing algorithm and how to overcome them?

What are the limitations of the hill climbing algorithm? How can we overcome these limitations?
9
votes
1answer
569 views

What are Hyper-heuristics?

I wanted to know what the differences between hyper-heuristics and meta-heuristics are, and what their main applications are. Which problems are suited to be solved by Hyper-heuristics?
8
votes
1answer
375 views

What are the implications of the “No Free Lunch” theorem for machine learning?

The No Free Lunch (NFL) theorem states (see the paper Coevolutionary Free Lunches by David H. Wolpert and William G. Macready) any two algorithms are equivalent when their performance is averaged ...
7
votes
1answer
221 views

Why does a one-layer hidden network get more robust to poor initialization with growing number of hidden neurons?

In a nutshell: I want to understand why a one hidden layer neural network converges to a good minimum more reliably when a larger number of hidden neurons is used. Below a more detailed explanation of ...
7
votes
1answer
411 views

Why does 'loss' change depending on the number of epochs chosen?

I am using Keras to train different NN. I would like to know why if I increment the epochs in 1, the result until the new epoch is not the same. I am using shuffle=False, and np.random.seed(2017), and ...
7
votes
3answers
97 views

How much can the addition of new features improve the performance?

How much can the addition of new features improve the performance of the model during the optimization process? Let's say I have a total of 10 features. Suppose I start the optimisation process using ...
5
votes
1answer
1k views

Why number of hidden units in a layer are suggested to be in powers of 2?

It is suggested that the number of hidden units in a layer should be in powers of 2 because it helps converge faster. Is it a fact and if it is, how this helps the NN learn faster. Does it have to do ...
5
votes
1answer
3k views

How to avoid falling into the “local minima” trap?

How do I avoid my gradient descent algorithm into falling into the "local minima" trap while backpropogating on my neural network? Are there any methods which help me avoid it?
5
votes
1answer
236 views

When should we use algorithms like Adam as opposed to SGD?

As far as I know, Stochastic Gradient Descent is an optimization algorithm which belongs to the the category of algorithms where hyper-parameters have to be defined beforehand. They are useful in many ...
5
votes
1answer
656 views

How can we use linear programming to solve an MDP?

Apparently, we can solve an MDP (that is, we can find the optimal policy for a given MDP) using a linear programming formulation. What's the basic idea behind this approach? I think you should start ...
5
votes
1answer
38 views

How can we conclude that an optimization algorithm is better than another one

When we test a new optimization algorithm, what the process that we need to do?For example, do we need to run the algorithm several times, and pick a best performance,i.e., in terms of accuracy, f1 ...
5
votes
1answer
109 views

Reproduce Firefly Algorithm experiments of original paper?

I have been trying to reproduce the experiments done in the original: "Firefly Algorithm for multimodal optimization" (linked in the question) so far: unsuccessfully. For the moment being I'm okay if ...
4
votes
4answers
422 views

What is the actual learning algorithm: back-propagation or gradient descent?

What is the actual learning algorithm: back-propagation or gradient descent (or, in general, the optimization algorithm)? I am reading through chapter 8 of Parallel Distributed Processing hand book ...
4
votes
2answers
92 views

Can we optimize an optimization algorithm?

In this answer to the question Is an optimization algorithm equivalent to a neural network?, the author stated that, in theory, there is some recurrent neural network that implements a given ...
4
votes
1answer
49 views

What are examples of optimization problems that can be solved using a genetic algorithm?

I'm trying to learn how a genetic algorithm can solve optimization problems. I have already learned how a genetic algorithm can solve knapsack, TSP and set cover problems. I'm looking for some other ...
4
votes
1answer
93 views

What is the basic purpose of local search methods?

I read about the hill climbing algorithms, the simulating annealing algorithm, but I am confused. What is the basic purpose of local search methods?
4
votes
1answer
37 views

How to use MOPSO to align characters vertically?

I need to efficiently align characters vertically using Multi Objective PSO. Alignment is achieved by adding spaces in between a given set of characters. ...
3
votes
2answers
166 views

Is an evaluation function as good as an optimization function

I have been so for self-learning basic A.I concepts and would like to know if having a really good evaluation function as good as any of alpha-beta pruning optimization functions such as killer moves, ...
3
votes
2answers
65 views

Is there a way to define the boundaries of the optimal size of a training set?

At a related question in Computer Science SE, a user told: Neural networks typically require a large training set. Is there a way to define the boundaries of the "optimal" size of a training set ...
3
votes
2answers
60 views

Could error surface shape be useful to detect which local minima is better for generalization?

The following plot shows error function output based on system weights. Two equal local minima are shown in green pointers. Note that the red dots are not related to the question. Does the right one ...
3
votes
1answer
62 views

What are the methods of optimizing overfitted models?

I'm worrying that my network has become too complex. I don't want to end up with half of the network doing nothing but just take up space and resources. So, what are the techniques for detecting and ...
3
votes
1answer
151 views

What's the difference between RMSE and Euclidean distance, and when to use a custom loss? [closed]

I'm searching for a loss function that fits my project. Actually, I have two questions, but they are in the same direction. I take a look at the definition of the root mean squared error (RMSE) and ...
3
votes
1answer
43 views

Maximizing or Minimizing in Trust Region Policy Optimization?

I happened to discover that the v1 (19 Feb 2015) and the v5 (20 Apr 2017) versions of TRPO papers have two different conclusions. The Equation (15) in v1 is $\min_\theta$ while the Equation (14) in v2 ...
3
votes
1answer
49 views

Is it possible to have a dynamic $Q$-function?

I am trying to use Q-learning for energy optimization. I only wish to have states that will be visited by the learning agent, and, for each state, I have a function that generates possible actions, so ...
3
votes
1answer
72 views

Genetic Algorithms: Trade-off between time and variance with regards to fitness function

I'm developing an AI to play a card game with a genetic algorithm. Initially, I will evaluate it against a player that plays randomly, so there will naturally be a lot of variance in the results. I ...
3
votes
1answer
72 views

Advantages of Kullback-Leibler over L1/L2?

I've recently encounter different articles that are recommending to use KL instead of L1/L2 norm when trying to minimize a probability distribution. But none of the articles are giving a clear ...
3
votes
1answer
134 views

Why does hill climbing algorithm only produce a local maximum?

Apparently, the hill climbing algorithm just produces a local maximum, and not necessarily a global optimum. It's stuck on a local maximum. Why does hill climbing algorithm only produce a local ...
2
votes
1answer
124 views

If Deep Learning is non convex, then why use convex loss?

I was just reading through some convex optimization textbooks to hopefully improve my deep learning understanding and come up with new ideas. Halfway through, I decided to Google a bit! It's obvious ...
2
votes
1answer
52 views

Method to check goodness of combinatorial optimization algorithm implementation

How do I check which algorithm solves my problem best? Given a optimaization problem, I apply different well known optimization algorithms (genetic algorithm, simulated annealing, ant colony etc.) to ...
2
votes
3answers
87 views

Would a sentient AI try to create a more optimised AI which would eventually overtake AI 1.0?

Would AI be a self-propogating iteration in which the previous AI is destroyed by a more optimised AI child? Would the AI have branches of it's own AI warning not to create the new AI?
2
votes
1answer
86 views

Is a calculus or ML approach to varying learning rate as a function of loss and epoch been investigated?

Many have examined the idea of modifying learning rate at discrete times during the training of an artificial network using conventional back propagation. The goals of such work have been a balance ...
2
votes
1answer
213 views

How can we calculate the gradient of the Boltzmann policy over reward function?

I'm struggling with an inverse reinforcement learning problem which seems to appear quite often around the literature, yet I can't find any resources explaining it. The problem is that of calculating ...
2
votes
1answer
202 views

Problems getting ADADELTA to converge

I have followed the pseudocode in the ADADELTA paper (top right on page 3), and wrote the following Python code for solving the optimization problem L(x) = x^2: ...
2
votes
1answer
779 views

Are FFNN (MLP) Lipschitz functions?

My question is regarding standard dense-connected feed forward neural networks with sigmoidal activation. I am studying Bayesian Optimization for hyper-parameter selection for neural networks. There ...
2
votes
2answers
67 views

Why is a mix of greedy and random usually “best” for stochastic local search?

I read that a mix of "greedy" and "random" are ideal for stochastic local search (SLS), but I'm not sure why. It mentioned that the greedy finds the local minima and the randomness avoids getting ...
2
votes
1answer
55 views

How can we reach global optimum?

Gradient descent can get stuck into local optimum. Which techniques are there to reach global optimum?
2
votes
1answer
43 views

Recent Python Packages for Random Search Optimization

Which python packages do you recommend on random search optimization to use? Is there any recent and good one (better than the one in Sci-kit)?
2
votes
1answer
121 views

Training an artificial neural network using PSO

Hi guys I've been studying such combination where the idea is to replace the classic descendant gradient for an algorithm that is less sensitive to local optimum, so the PSO tries to select the best ...
2
votes
2answers
268 views

When should I use simulated annealing as opposed to a genetic algorithm?

What kind of problems is simulated annealing better suited for compared to genetic algorithms? From my experience, genetic algorithms seem to perform better than simulated annealing for most problems....
2
votes
1answer
42 views

How do I compute log-likelihood for training set in supervised learning?

I am building a supervised learning model and I wish to compute the log-likelihood for the training set at the point of the minimum validation error. Initially, I was computing the sum of all the ...
2
votes
2answers
417 views

Input optimization on a supervised learning system

Problem Given a collection of pairs (X, y) where X belongs to R^n and y belongs to R, find the X such that the associated y would be maximum. Example Given: (X=(1, 2), y=-9) (X=(-2, 4), y=-36) (X=...
2
votes
1answer
77 views

How to find proper parameter settings for a given optimization algorithm?

Is there any methodology to find proper parameter settings for a given meta-heuristic algorithm, eg. Firefly Algorithm or Cuckoo Search? Is this an open issue in optimization? Is extensive ...
2
votes
0answers
28 views

Is logistic regression used for unconstrained or constrained optimisation problems?

Is logistic regression used for unconstrained or constrained optimization problems, and why?
2
votes
1answer
32 views

Metrics of quality of parameter space exploration

Considering a black box optimization problem on non-linear, non-convex function where we want to minimize an objective function. One way to assess the quality of an optimizer is to look at the best ...
2
votes
0answers
48 views

Does Retina-net's focal loss accomplish its goal?

Taking out the weighting factor we can define focal loss as $$FL(p) = -(1-p)^\gamma log(p) $$ Where $p$ is the target probability. The idea being that single stage object detectors have a huge ...
2
votes
0answers
46 views

Is a neural network the correct approach to optimising a fitness function in a genetic algorithm?

I've written an application to help players pick the optimal heroes during the draft phase of the Heroes of the Storm MOBA. It can be daunting to pick from 80+ characters that have synergies/counters ...
2
votes
0answers
33 views

Can we use the Tierra approach to optimize machine code?

Thomas Ray's Tierra is a computer program which simulates life. In the linked paper, he argues how this simulation may have real-world applications, showing how his digital organisms (computer ...
2
votes
0answers
78 views

Is a very powerful oracle sufficient to trigger the AI singularity?

Lets say we have a oracle $S$ that, given any function $F$ and desired output $y$, can find an input $x$ that causes $F$ to output $y$ if it exists, or otherwise returns nil. I.e.: $$S(F, y) = x \...