Skip to main content

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
1 vote
0 answers
286 views

Could the Jensen-Shannon divergence and Kullback-Leibler divergence be used as loss functions of non-generation problems?

If I understand correctly, the KL divergence is a measure of information loss between a ground truth distribution $P$ and a predicted distribution $Q$, and the Jensen-Shannon divergence is the mean of ...
ashenoy's user avatar
  • 1,419
1 vote
1 answer
1k views

Query regarding the minmax loss function formulation of the training of a Generative Adversarial Network (GAN) [closed]

Just needed a clarification on the training procedure for a standard GAN. Of my understanding the loss function to optimize is a min max (max min causing mode collapse due to focus on one class ...
ashenoy's user avatar
  • 1,419
3 votes
1 answer
216 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 ...
EArwa's user avatar
  • 77
2 votes
0 answers
62 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 ...
Richard Nienaber's user avatar
4 votes
1 answer
127 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 ...
olinarr's user avatar
  • 755
1 vote
1 answer
320 views

How does NEAT find the most successful generation without gradients?

I'm new to NEAT, so, please, don't be too harsh. How does NEAT find the most successful generation without gradient descent or gradients?
Sebastian Dixon's user avatar
2 votes
2 answers
382 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 ...
Gooby's user avatar
  • 351
1 vote
0 answers
36 views

Estimating Baselines using ALS

I am trying to figure out how ALS works when minimizing the following formula: $\\ \\$ $\text{min}_{\lbrace b_u,b_i \rbrace} \sum_{(u,i)\in \mathcal{K}} (r_{ui} - \bar{r} - b_u - b_i )^2 + \lambda_{...
NaveganTeX's user avatar
1 vote
2 answers
557 views

How to properly optimize shared network between actor and critic?

I'm building an actor-critic reinforcement learning algorithm to solve environments. I want to use a single encoder to find representation of my environment. When I share the encoder with the actor ...
BestR's user avatar
  • 183
9 votes
3 answers
3k views

How is it possible that the MSE used to train neural networks with gradient descent has multiple local minima?

We often train neural networks by optimizing the mean squared error (MSE), which is an equation of a parabola $y=x^2$, with gradient descent. We also say that weight adjustment in a neural network by ...
isnvi23h4's user avatar
  • 213
-1 votes
2 answers
3k views

How can the A* algorithm be optimized?

How can the A* algorithm be optimized? Any references that shows the optimization of A* algorithm are also appreciated.
Lexi's user avatar
  • 109
1 vote
1 answer
209 views

How can we reach global optimum?

Gradient descent can get stuck into local optimum. Which techniques are there to reach global optimum?
hina munir's user avatar
1 vote
1 answer
968 views

Why isn't the reverse KL divergence commonly used in supervised learning?

Forward KL Divergence (also known as cross entropy loss) is a standard loss function in supervised learning problems. I understand why it is so: matching a known a trained distribution to a known ...
cgo's user avatar
  • 185
0 votes
1 answer
1k views

How could we solve the TSP using a hill-climbing approach?

How could we solve the TSP using a hill-climbing approach?
dua fatima's user avatar
6 votes
1 answer
3k 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 ...
Utku's user avatar
  • 173
5 votes
1 answer
7k 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 ...
nbro's user avatar
  • 40.9k
1 vote
0 answers
25 views

What is the purpose of the new neurons in the constrained neural network?

I would like to train a constrained neural network. I found a paper on this: https://papers.nips.cc/paper/4-constrained-differential-optimization.pdf. However, I don't really understand how to change ...
Gesetzt's user avatar
  • 41
1 vote
1 answer
96 views

Which local minima to choose according to the shape of the error surface?

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. Considering the ...
hmojtaba's user avatar
4 votes
2 answers
133 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 ...
hmojtaba's user avatar
2 votes
0 answers
224 views

Any guidance on learning rate / batch size for noisy data (high Bayes error rate)?

Is there any guidance available for training on very noisy data, when Bayes error rate (lowest possible error rate for any classifier) is high? For example, I wonder if deliberately (not due to memory ...
Xpector's user avatar
  • 161
2 votes
0 answers
149 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 \...
Phylliida's user avatar
  • 274
1 vote
0 answers
23 views

Feature visualization on neural networks which are not for classification

Feature visualization allows to better understand neural networks by generating images that maximize the activation of a specific neuron, and therefore understand what are the abstract features that ...
firion's user avatar
  • 269
2 votes
1 answer
121 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 ...
Bryan McGill's user avatar
2 votes
1 answer
91 views

How can a specific connectivity pattern be stored in an optimally compact representation?

I am interested in optimizing the memory capacity of an AGI. Given a specific complex input an AI can create a simplified model. This is a problem that can be solved using sparse coding [1]. However, ...
noumenal's user avatar
  • 137
1 vote
0 answers
37 views

Classical Internet routing vs. Swarm routing (such as Ant routing)?

Is it possible to mention the drawbacks/advantages of Swarm routing (such as Ant routing etc) in comparison with classical routing algorithms in communication networks in a general view? In other ...
Questioner's user avatar
4 votes
2 answers
5k 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....
Abbas Ali's user avatar
  • 566
2 votes
1 answer
2k views

Neural Network Optimizers in Reinforcement Learning non-well behaved environments

https://stackoverflow.com/questions/36162180/gradient-descent-vs-adagrad-vs-momentum-in-tensorflow Here, the nice gifs explain how different algorithms approach towards the root. Unfortunately, the ...
sagar_acharya's user avatar
3 votes
1 answer
1k views

Why does the 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 ...
user29521's user avatar
1 vote
0 answers
25 views

What does it essentially mean if the neural network has convex error surface?

Suppose if I am building a Linear Regression model with one fully connected layer and a sigmoid with minimizing mean squared error as objective. Why would the error surface be convex? Does finding ...
backprop7's user avatar
4 votes
1 answer
238 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?
Iram Shah's user avatar
  • 315
7 votes
1 answer
16k views

What is an objective function?

Local search algorithms are useful for solving pure optimization problems, in which the aim is to find the best state according to an objective function. My question is what is the objective function?
Abbas Ali's user avatar
  • 566
2 votes
1 answer
108 views

Reinforcement Learning to Grouped Scheduling Optimisation Problem

I am not sure the name of this kind of problem, but anyway, the situation is as below. Assign teachers into Groups and consider on each of their workload, availability etc. There are some other soft/...
Wesley Tsang's user avatar
10 votes
2 answers
26k 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?
Abbas Ali's user avatar
  • 566
5 votes
3 answers
2k 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 ...
Sreedhar Veluri's user avatar
5 votes
2 answers
181 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 ...
Miko Diko's user avatar
  • 177
1 vote
1 answer
23 views

AI that maximizes the storage of rectangular parallelepipeds in a bigger parallelepiped

As you can see in the title, I'm trying to program an AI in Java that would help someone optimize his storage. The user has to enter the size of his storage space (a box, a room, a warehouse, etc...) ...
Nawra C's user avatar
  • 33
0 votes
1 answer
2k views

What are the advantages and disadvantages of using LISP for constraint satisfaction in 3D space

We are currently working on developing a 3D modeling software that allows designers to set spatial constraints to models. The computer then should generate a 3D mesh conforming to these constraints. ...
Shashank Gargeshwari's user avatar
2 votes
2 answers
2k views

How do I optimize a specific function using a genetic algorithm?

I recently learned about genetic algorithms and I solved the 8 queens problem using a genetic algorithm, but I don't know how to optimize any functions using a genetic algorithm. $$ \begin{array}{r} \...
Evan Pk's user avatar
  • 29
0 votes
1 answer
85 views

What is the difference between the study of evolutionary algorithms and optimization?

I have a course named "Evolutionary Algorithms", but our teacher is always mentioning the word "optimization" in his lectures. I am confused. Is he actually teaching optimization? If yes, why is the ...
user avatar
2 votes
1 answer
119 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 ...
Douglas Daseeco's user avatar
10 votes
1 answer
4k 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 ...
imflash217's user avatar
4 votes
1 answer
139 views

What AI technique should I use to assign a person to a task?

I'm trying to learn AI and thinking to apply it to our system. We have an application for the translation industry. What we are doing now is the coordinator $C$ assigns a file to a translator $T$. The ...
Jaime Sangcap's user avatar
4 votes
1 answer
124 views

Can I compute the fitness of an agent based on a low number of runs of the game?

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 ...
OrangeMan's user avatar
  • 237
2 votes
1 answer
521 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 ...
Akhilesh Pandey's user avatar
1 vote
0 answers
61 views

Optimization step in Apprenticeship Learning via Inverse Reinforcement Learning

Why the optimization step of the algorithm a quadratic program? [See: Apprenticeship Learning via Inverse Reinforcement Learning; page 3] Isn't the objective function linear? Why don't we treat ...
İbrahim Abbasov's user avatar
3 votes
1 answer
81 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 ...
fish_tree's user avatar
  • 247
2 votes
1 answer
538 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 ...
Dominus's user avatar
  • 123
2 votes
1 answer
661 views

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

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 ...
Amir Hossein F's user avatar
0 votes
1 answer
97 views

Can TensorFlow minimize "symbolically" [closed]

From https://stackoverflow.com/questions/36370129/does-tensorflow-use-automatic-or-symbolic-gradients, I understood TensorFlow requires all the operations in the Graph to be explicit formulas (instead ...
ZisIsNotZis's user avatar
3 votes
2 answers
897 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=...
Mark's user avatar
  • 33