Questions tagged [constrained-optimization]

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

Filter by
Sorted by
Tagged with
1 vote
0 answers
62 views

Is this a bandit problem or a MDP?

I am trying to understand if this problem can be casted both as a bandit problem as well as an MDP. Lets assume that we are trying to optimize sales $y_t$ based on investments $x_{1, t}, x_{2, t}$ ...
hugh's user avatar
  • 53
0 votes
0 answers
26 views

Can we derive the support vector machines dual formulation without directly using lagrangian duality theory?

Lagrangian duality theory allows us to derive the dual formulation for support vector machines and to show that the primal and the dual solutions are equivalent. My question is: is it possible to ...
Papyrus's user avatar
0 votes
0 answers
36 views

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 ...
Donatas Šimeliūnas's user avatar
0 votes
0 answers
175 views

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 ...
Cloudy's user avatar
  • 213
1 vote
0 answers
75 views

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 ...
Sobhan's user avatar
  • 111
0 votes
0 answers
71 views

For simple weight constraints: Add constraint directly or use parameterization without constraint

I am wondering if it makes sense to parameterize simple weight inequalities, for example if the weights should be $w\geq 0$, one cound train $\exp w$ over the unconstrained set instead. Also, if $\sum ...
Philipp123's user avatar
2 votes
0 answers
30 views

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 ...
vgoklani's user avatar
  • 121
0 votes
0 answers
100 views

How to assign tasks to users with ranking?

I'm trying to write an automatic assignment algorithm for the following problem: I have $N$ tasks and $M$ users. For each task, I have a ranking for each user for "how related it is to that user&...
Bob Sacamano's user avatar
4 votes
2 answers
218 views

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 ...
user3489173's user avatar
3 votes
1 answer
333 views

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(...
josealeixo.pc's user avatar
3 votes
1 answer
820 views

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 ...
ycenycute's user avatar
  • 341
2 votes
2 answers
378 views

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,...
Tariq Kavish Arain's user avatar
9 votes
1 answer
149 views

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 ...
Ramzah Rehman's user avatar
1 vote
0 answers
33 views

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 ...
Subho's user avatar
  • 41
2 votes
2 answers
96 views

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 ...
Alan's user avatar
  • 21
2 votes
1 answer
399 views

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 ...
CharcoalG's user avatar
  • 121
4 votes
2 answers
2k views

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-...
Kevvy Kim's user avatar
  • 141
3 votes
2 answers
1k views

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 ...
John Watts's user avatar