Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Questions tagged [constrained-optimization]

For questions that involve constrained optimization problems (in the context of artificial intelligence).

18 questions
9
votes
1 answer

Given a list of integers $\{c_1, \dots, c_N \}$, how do I find an integer $D$ that minimizes the sum of remainders $\sum_i c_i \text{ mod } D$?

I have a set of fixed integers $S = \{c_1, \dots, c_N \}$. I want to find a single integer $D$, greater than a certain threshold $T$, i.e. $D > T \geq 0$, that divides each $c_i$ and leaves remainder $r_i \geq 0$, i.e. $r_i$ can be written as $r_i =…
Ramzah Rehman
  • 91
  • 4
4
votes
2 answers

How do we design a neural network such that the $L_1$ norm of the outputs is less than or equal to 1?

What are some ways to design a neural network with the restriction that the $L_1$ norm of the output values must be less than or equal to 1? In particular, how would I go about performing back-propagation for this net? I was thinking there must be…
Kevvy Kim
  • 141
  • 3
4
votes
2 answers

Which neural network can I use to solve this constrained optimisation problem?

Let $\mathcal{S}$ be the training data set, where each input $u^i \in \mathcal{S}$ has $d$ features. I want to design an ANN so that the cost function below is minimized (the sum of the square of pairwise differences between model outputs) and the…
user3489173
  • 179
  • 6
3
votes
2 answers

How to use a VAE to reconstruct an image starting from an initial image instead of starting from a random vector?

Is it possible to use a VAE to reconstruct an image starting from an initial image instead of using K.random_normal, as shown in the “sampling” function of this example? I have used a sample image with the VAE encoder to get z_mean and z_logvar. I…
John Watts
  • 31
  • 2
3
votes
1 answer

How to use DQN when the action space can be different at different time steps?

I would like to employ DQN to solve a constrained MDP problem. The problem has constraints on action space. At different time steps till the end, the available actions are different. It has different possibilities as below. 0, 1, 2, 3, 4 0, 2, 3,…
ycenycute
  • 341
  • 1
  • 2
  • 6
2
votes
0 answers

How to create a loss function that penalizes duplicate indices in the output tensor?

We're working on a sequence-to-sequence problem using pytorch, and are using cross-entropy to calculate the loss when comparing the output sequence to the target sequence. This works fine and penalizes the model correctly. However, we also have the…
vgoklani
  • 121
  • 2
2
votes
1 answer

Intuition behind $1-\gamma$ and $\frac{1}{1-\gamma}$ for calculating discounted future state distribution and discounted reward

In the appendix of the Constrained Policy Optimization (CPO) paper (Arxiv), the authors denote the discounted future state distribution $d^\pi$ as: $$d^\pi(s) = (1-\gamma) \sum_{t=0}^\infty{\gamma^t P(s_t = s \vert \pi)}\tag1$$ and the discounted…
josealeixo.pc
  • 205
  • 1
  • 6
2
votes
2 answers

How can we design the mutation and crossover operations when the order of the genes in the chromosomes matters?

Consider an optimization problem that involves a set of tasks $T = \{1,2,3,4,5\}$, where the goal is to find a certain order of these tasks. I would like to solve this problem with a genetic algorithm, where each chromosome $C = [i, j, k, l, m]$…
Tariq Kavish Arain
  • 41
  • 4
2
votes
2 answers

How does one make a neural network learn the training data while also forcing it to represent some known structure?

In general, how does one make a neural network learn the training data while also forcing it to represent some known structure (e.g., representing a family of functions)? The neural network might find the optimal weights, but those weights might no…
Alan
  • 21
  • 1
2
votes
1 answer

How to handle infeasibility caused due to crossover and mutation in genetic algorithm for optimization?

I have chromosomes with floating-point representation with values between $0$ and $1$. For example Let $p_1 = [0.1, 0.2, 0.3]$ and $p_2 = [0.5, 0.6, 0.7]$ be two parents. Both comply with the set of constraints. In my case, the major constraint is…
CharcoalG
  • 21
  • 2
1
vote
0 answers

What would be a good optimization technique for this kind of problem?

Problem Description: Since I am not sure if there is a scientific term that categorizes this problem, I will do my best to describe it thoroughly. Suppose there is a chamber that's being filled with poisonous gas. The amount of poisonous gas being…
Sobhan
  • 111
  • 3
1
vote
0 answers

Wasserstein GAN with non-negative weights in the critic

I want to train a WGAN where the convolution layers in the critic are only allowed to have non-negative weights (for a technical reason). The biases, nonetheless, can take both +/- values. There is no constraint on the generator weights. I did a toy…
Subho
  • 41
  • 2
0
votes
0 answers

Inquiry about utilising AI in CNC machining path generation

I will begin by describing a situation. I work in laser machining control company. The essence of the problem, to which I would like to try to apply AI based tool is this: Say I have a analytically described trajectory in 3D space. It can consist of…
Donatas Šimeliūnas
  • 1
  • 2
0
votes
0 answers

Intuition behind replacing constraint in equation for Optimal Separating Hyperplane

I am reading "Optimal Separating Hyperplane" section of the book - Elements of Statistical Learning which is described on page 132 as follows: My questions: The constraint $||\beta|| = 1$ is removed from eq. 4.45 by introducing $1/||\beta||$ in…
Deepak Tatyaji Ahire
  • 101
  • 1
0
votes
0 answers

Why do Soft Actor-Critic with automatic temperature tuning use only a single dual variable?

In section 5 of the paper “Soft Actor Critic Algorithms and Applications”, the authors propose to optimize the policy subject to the constraints that the entropy of action distribution should be greater than a specific value…
Cloudy
  • 203
  • 1
  • 5
1
2