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
1answer
20 views

What is the role of convex optimisation in AI systems?

Convex optimisation is defined as: I have seen a lot of talk about convex loss functions in Neural Networks and how we are optimising rewards or penalty in AI/ML systems. But I have never seen any ...
0
votes
2answers
23 views

How can I train a neural network if I don't have enough data?

I have created a neural network that is able to recognize images with the numbers 1-5. The issue is that I have a database of 16x5 images which ,unfortunately, is not proving enough as the neural ...
2
votes
1answer
71 views

Which deep reinforcement learning algorithm is appropriate for my problem?

My task is to solve an optimization problem with deep reinforcement learning. I read about several algorithms like DQN, PPO, DDPG, and A2C/A3C but use cases always seem to be problems like video games ...
2
votes
1answer
40 views

What effect does batch norm have on the gradient?

Batch norm is a technique where they essentially standardize the activations at each layer, before passing it on to the next layer. Naturally, this will affect the gradient through the network. I have ...
2
votes
1answer
56 views

Why does variational auto-encoder use the reconstruction loss?

VAE is trained to reduce the following two losses. KL divergence between inferred latent distribution and Gaussian. the reconstruction loss I understand that the first one regularizes VAE to get ...
0
votes
1answer
22 views

Oscillating around the saddle point in gradient descent?

I was reading a blog post that talked about the problem of the saddle point in training. In the post, it says if the loss function is flatter in the direction of x (local minima here) compared to ...
1
vote
3answers
41 views

Object Detection and Choice of Optimizer

Suppose that we have different animals that we have 4 types of dogs that we want to detect (Golden Retriever, Black Labrador, Cocker Spaniel, and Pit Bull). The training data consists of png images of ...
1
vote
3answers
46 views

What kind of optimizer is suggested to use for binary classification of similar images?

I have spent some time searching Google and wasn't able to find out what kind of optimization algorithm is best for binary classification when images are similar to one another. I'd like to read ...
1
vote
1answer
647 views

What are the properties of hill climbing?

What are the properties of hill climbing? More precisely, does it encounter any of the following phenomena? Local maxima Inadmissible heuristic Ridges Plateau
1
vote
0answers
30 views

Are there optimizers that schedule their learning rate, momentum etc. autonomously?

I'm aware there are some optimizer such as Adam that adjust the learning rate for each dimension during training. However, afaik, the maximum learning rate they can have is still determined by the ...
2
votes
1answer
57 views

What are advantages of using meta-heuristic algorithms on optimization problems?

What are the advantages and disadvantages of using meta-heuristic algorithms on optimization problems? Simply, why do we use meta-heuristic algorithms, like PSO, over traditional mathematical ...
2
votes
1answer
38 views

In deep learning, is it possible to use discontinuous activation functions?

In deep learning, is it possible to use discontinuous activation functions (e.g. one with jump discontinuity)? (My guess : for example, ReLU is non-differentiable at a single point, but it still has ...
2
votes
2answers
92 views

Solving a planning if finding the goal state is part of the problem

I having trouble finding some starting points for solving an occupancy problem which seems like a good candidate for ai. Assume the following situation: In a company I have n cars and m employees. ...
2
votes
1answer
34 views

When training a CNN, what are the hyperparameters to tune first?

I am training a convolutional neural network for object detection. Apart from the learning rate, what are the other hyperparameters that I should tune? And in what order of importance? Besides, I read ...
0
votes
0answers
14 views

Optimizer effects on neural network with two outputs

I'm confused about the following issue. Let assume that we have a neural network that takes one input and two outputs. I try to visualize my model like as follows: ...
1
vote
0answers
25 views

Imposing contraints on sequence of image classifications

Are there example implementations of networks that apply constraints across sequences of image classifications where class labels are ordinal numbers? For example, to cause the output of a CNN to ...
1
vote
1answer
33 views

How should I weight the factors that affect the choice of an action in a strategy board game with multiple actions?

I have written an AI that plays a strategy board game. There are lots of different types of moves (e.g. attack, defend, help ally colony, etc.). I calculate the best moves to do depending on a ...
2
votes
0answers
30 views

Is logistic regression used for unconstrained or constrained optimisation problems?

Is logistic regression used for unconstrained or constrained optimization problems, and why?
3
votes
1answer
280 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 ...
1
vote
0answers
111 views

How can I assign agents to tasks based on time and affinity?

I am working on an assignment problem. Consider $K$ agents $A_1, \dots A_K$ and $N$ tasks $T_1, \dots T_N$. Each task has a certain time $t(T_i)$ to be completed and each agent has a matching (or ...
1
vote
0answers
30 views

How does the automated temperature adjustment step work in Soft Actor-Critic?

In section 5 of the paper Soft Actor-Critic Algorithms and Applications, it is proposed an optimization problem to obtain an optimal temperature parameter $\alpha^*_t$. First, one uses the original ...
1
vote
0answers
57 views

Grey Wolf Optimization - Issue with Dimension [closed]

I'm trying to use the grey wolf optimization (GWO) for texts clustering. I used this code, https://github.com/7ossam81/EvoloPy-NN/blob/master/selector.py I tried using the dimension 30 for the GWO as ...
0
votes
0answers
14 views

Choosing best combinations from all possible combination expressions based few variables, unary operators, binary operators

I have a few financial variables of a stock universe like OHLC prices, volume, and other fundamentals with varying time-frequency. Using this set I'm creating an expression that gives the weights to ...
4
votes
1answer
52 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 ...
10
votes
1answer
495 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 ...
5
votes
1answer
42 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 ...
0
votes
2answers
169 views

LSTM network doesn't converge, what should be changed? [closed]

I'm testing out TensorFlow LSTM layer text generation task, not classification task; but something is wrong with my code, it doesn't converge. What changes should be done? Source code: ...
2
votes
1answer
37 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 ...
1
vote
0answers
35 views

why the sigmoid function will be 1 and 0 if we use a fully connected layer that produce a big enough positive(res negative )output

HI I am using a fully connected network that uses sigmoid if we feed a a big enough weights the sigmoid function will finally become 1 or 0 , is there any solution to avoid this ? and will this lead ...
3
votes
1answer
187 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 ...
1
vote
1answer
122 views

Create optimizer object using the tf.keras.optimizers.get function [closed]

I am trying to have the type of optimizer as a variable in the hyperparameter tuning phase. For that reason I am trying to use the tf.keras.optimizer.get function ...
-3
votes
3answers
246 views

Evolutionary neural architecture?

I'm working on an idea for an AI architecture, and would like to know if there are any apparent flaws, or if there is prior work in this vein. Set I/O so that the neural network can read and write ...
2
votes
0answers
55 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 ...
1
vote
0answers
30 views

Is convergence to a local minima more likely with transfer learning?

While doing transfer learning where my two problems are face-generation and car-generation is it likely that, if I use the weights of one problem as the initialization of the weights for the other ...
0
votes
0answers
15 views

Derivation for Value Iteration of CVaR

I am reading a paper named Risk-sensitive and Robust Decision-making: a CVaR Optimization Approach. In appendix A.3 they provide a proof for their Theorem $4$. The $n=1$ case for equation (11) is ...
1
vote
0answers
78 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 ...
4
votes
2answers
98 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 ...
0
votes
1answer
140 views

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

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 ...
1
vote
1answer
57 views

Is an optimization algorithm equivalent to a neural network?

Is an optimization algorithm equivalent to a neural network?
3
votes
1answer
91 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 ...
2
votes
0answers
47 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 ...
4
votes
1answer
56 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 ...
0
votes
0answers
23 views

Custom optimizer and word-vector evaluator lstm

I’m using Keras LSTM layers and building a model that is trained off ethics text. I have a problem of often over fitting (the network basically remembers my input corpus as it is very small). I was ...
1
vote
1answer
79 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?
2
votes
2answers
78 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 ...
1
vote
0answers
14 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_{...
1
vote
1answer
43 views

How to properly optimize shared network between actor and critic?

I'm building an actor-critic reinforcment 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 ...
0
votes
2answers
64 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.
2
votes
1answer
57 views

How can we reach global optimum?

Gradient descent can get stuck into local optimum. Which techniques are there to reach global optimum?
0
votes
1answer
500 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 ...