Questions tagged [constrained-optimization]
For questions that involve constrained optimization problems (in the context of artificial intelligence).
14
questions
0
votes
0
answers
9
views
Stopping criteria for SMO when no solution exists for Hard Margin SVM
When we solve the dual problem using SMO, we pick two $\mu_i$'s at a time and optimize the dual wrt them while satisfying the required constraints.
But in case we are using the no slack formulation of ...
0
votes
0
answers
15
views
How can TRPO with constrained form allow larger update step?
There are two optimization forms of TRPO.
One is that:
\begin{equation}\max\limits_{\theta}[L_{\theta_{old}}(\theta) - CD^{max}_{KL}(\theta_{old}, \theta)]\end{equation} where $C = \frac{4\epsilon\...
0
votes
0
answers
12
views
Incorporate specific constraints while training a (Conditional) variational autoencoder
I'm wondering how could I incorporate specific constraints during the training phase of a deep learning model.
In particular, I work for a materials-science related project where I feed to my models ...
0
votes
0
answers
63
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&...
0
votes
0
answers
6
views
How much depth is recommended to study constrained optimization for deep learning?
I am studying the chapter named Numerical Computation from the deep learning textbook
In the chapter, there is a section named Constrained Optimization. The authors recommended to read the portion of ...
4
votes
1
answer
129
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 ...
2
votes
1
answer
138
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(...
3
votes
1
answer
263
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 ...
2
votes
2
answers
149
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,...
9
votes
1
answer
134
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 ...
1
vote
0
answers
24
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 ...
2
votes
1
answer
133
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 ...
4
votes
2
answers
1k
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-...
3
votes
2
answers
815
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 ...