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
31 views

What are the conceptual differences between regularisation and optimisation in deep neural nets?

I'm trying to wrap my mind around the concepts of regularisation and optimisation in neural nets, especially around their differences. In my current understanding, regularisation is intended to tackle ...
0
votes
0answers
14 views

Good resources on building your own objective function? [closed]

So my understanding is ML is great for prediction, but seems like in a lot of cases, the focus is on minimizing MSE or something like entropy for a single predicted variable. For situations where ...
1
vote
0answers
39 views

What is the difference between exploitation and exploration in the context of optimization?

In the paper Moth-flame optimization algorithm: A novel nature-inspired heuristic paradigm (2015, published in Knowledge-Based Systems) The test functions are divided to three groups: unimodal, multi-...
0
votes
0answers
17 views

How to afine the extremity values in regression prediction with Keras?

I made a stack of bidirectional LSTM layers following by Dense layers (with swish activation functions) in order to predict a continuous value between 0 and 2. I compiled the model with ...
5
votes
2answers
63 views

Why perceptron criterion function is differentiable?

I'm reading the chapter one of the book called "Neural Networks and Deep Learning" from Charu C. Aggargal. In the section 1.2.1.1 of the book, I'm learning about the perceptron. One thing ...
2
votes
0answers
25 views

How are the lower and upper bound values of the moths determined in the Moth-Flame Optimization algorithm?

I am currently implementing the Moth-Flame Optimization (MFO) Algorithm, based on the paper: Moth-Flame Optimization Algorithm: A Novel Nature-inspired Heuristic Paradigm. To calculate the values of ...
3
votes
1answer
39 views

Measuring novel configuration of points

I am trying to implement Novelty search; I understand why it can work better than the standard Genetic Algorithm based solution which just rewards according to the objective. I am working on a problem ...
1
vote
0answers
11 views

Root finding in Deep Equilibrium Models

In the Deep Equilibrium Model the neural network can be seen as "infinitely deep". Training learns a nonlinear function as usual. But there is no forward propagation of input data through ...
1
vote
0answers
25 views

Why scaling down the parameter many times during training will help the learning speed be the same for all weights in Progressive GAN?

The title is one of the special things in Progressive GAN, a paper of the NVIDIA team. By using this method, they introduced that Our approach ensures that the dynamic range, and thus the learning ...
1
vote
1answer
53 views

Why is the learning rate generally beneath 1?

In all examples I've ever seen, the learning rate of an optimisation method is always less than $1$. However, I've never found an explanation as to why this is. In addition to that, there are some ...
0
votes
0answers
16 views

Partial pruning in counterfactual regret minimization (CFR)

I'm using CFR to solve a large imperfect-information game. One important technique for optimizing performance of this algorithm is "partial pruning", which allows the algorithm to skip ...
2
votes
2answers
103 views

How does PCA work when we reduce the original space to 2 or higher-dimensional space?

How does PCA work when we reduce the original space to a 2 or higher-dimensional space? I understand the case when we reduce the dimensionality to $1$, but not this case. $$\begin{array}{ll} \text{...
1
vote
2answers
28 views

Why does Simulated Annealing not take worse solution if the Energy Difference becomes higher?

In Simualated Annealing a worse solution is accepted with this probability: $p=e^{-\frac{E(y)-E(x)}{kT}}$. If that understanding is correct: Why is this probability function used? Because it means ...
1
vote
0answers
18 views

Which method of tree searching should be used for this board game?

Suppose the following properties of a board game: High branching factor in the beginning of the game (~500) which slowly tends towards 0 at the end of the game Evaluation of the any given board ...
0
votes
0answers
26 views

Binary data clustering by Matrix factorization

I have read an article talking about binary clustering using Matrix factorization(see attached), but i would like to understand some optimization concepts: Is it reasonable to use a Frobenius norm in ...
0
votes
0answers
22 views

Finding the energy function given update rule of a single layer non-linear neural network

Consider the network with N neurons, each of which takes a $2 \times k$ input specified by the tuple $(\vec c_t, \vec \theta_t)$ to produce output $\vec{R}_t$ through an update rule on the pairwise ...
1
vote
1answer
46 views

How could logistic loss be used as loss function for an ANN?

Normally, in practice, people use those loss functions with minima, e.g. $L_1$ mean absolute loss, $L_2$ mean squared error, etc. All those come with a minimum to optimize to. However, there's ...
1
vote
1answer
74 views

Does this $\max$ mean that we need to maximize the regret in this regret formula?

I found that the regret in Online Machine Learning is stated as: $$\operatorname{Regret}_{T}(h)=\sum_{t=1}^{T} l\left(p_{t}, y_{t}\right)-\sum_{t=1}^{T} l\left(h(x), y_{t}\right),$$ where $p_t$ is the ...
1
vote
1answer
38 views

How to optimize neural network parameters with REINFORCE

I've seen a few mentions in papers that neural network parameters can be found using REINFORCE algorithm. It was mentioned in the context of nondifferentiable operations involving e.g. step function ...
2
votes
1answer
52 views

If the normal equation works, why do we need gradient descent?

Recently, I followed the open course CS229, http://cs229.stanford.edu/notes/cs229-notes1.pdf This lecturer introduces an alternative approach to gradient descent that is called "Normal Equation&...
1
vote
1answer
54 views

Continuous state and continuous action Markov decision process time complexity estimate: backward induction VS policy gradient method (RL)

Model Description: Model based(assume known of the entire model) Markov decision process. Time($t$): Finite horizon discrete time with discounting factor State($x_t$): Continuous multi-dimensional ...
0
votes
2answers
76 views

How can I model this problem of delivering assets by choosing a route with reinforcement learning?

I would like to build a model based on reinforcement learning (RL) for the following scenario Recommend the best route (of cities listed for a given country) that satisfies the required criteria (...
0
votes
1answer
53 views

Can a machine learning approach solve this constrained optimisation problem?

I had done with different classification, regression and clustering approaches for predictions of values, etc. I was wondering if there is a machine learning approach for distribution of a whole based ...
1
vote
1answer
66 views

What is the difference between simulated annealing and deterministic annealing?

Not sure if this is the right place, but I was wondering if someone could briefly explain to me the differences & similarities between simulated annealing and deterministic annealing? I know that ...
1
vote
0answers
35 views

How many training runs are needed to obtain a credible value for performance?

I'm trying to optimize a neural network. For that, I'm changing parameters like the batch size, learning rate, weight initialization, etc. A neural network is not a deterministic algorithm, so, in ...
3
votes
0answers
70 views

How does SGD escape local minima?

SGD is able to jump out of local minima that would otherwise trap BGD I don't really understand the above statement. Could someone please provide a mathematical explanation for why SGD (Stochastic ...
2
votes
1answer
48 views

Which one is more important in case of different loss optimization algorithms, Speed or the Route?

We have different kinds of algorithms to optimize the loss like AdaGrad, SGD + Momentum, etc. Some are more commonly used than the others. In some algorithms, they usually range out before they ...
1
vote
0answers
43 views

Simplifying Log Loss

I am reading through a paper (https://www.mitpressjournals.org/doi/pdf/10.1162/0891201053630273) where they describe logloss as a ranking function and can be simplified to the margin of the training ...
0
votes
0answers
23 views

Which of these two strategies is the best to select solutions in simulated annealing?

I am using simulated annealing (SA) for an NP-hard combinatorial optimisation problem. 1) I am testing over a range of problem instances in which the objective values can be in the 100's or in the ...
0
votes
0answers
23 views

What are swarm optimization techniques used for: training the ANN by weight optimization or for feature selection?

Swarm intelligence (SI) is the collective behavior of decentralized, self-organized systems, natural or artificial. The concept is employed in work on artificial intelligence. SI-based algorithms, ...
0
votes
0answers
58 views

Can neural networks handle redundant inputs?

I have a fully connected neural network with the following number of neurons in each layer [4, 20, 20, 20, ..., 1]. I am using TensorFlow and the 4 real-valued ...
1
vote
3answers
99 views

How to improve neural network training against a large data set of points with varying magnitude

I am currently using TensorFlow and have simply been trying to train a neural network directly against a large continuous data set, e.g. $y = [0.014, 1.545, 10.232, 0.948, ...]$ corresponding to ...
1
vote
1answer
35 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 ...
2
votes
2answers
51 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
130 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 ...
4
votes
1answer
86 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 ...
1
vote
1answer
71 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
2k 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
2answers
853 views

For which of the following reasons can Hill Climbing get stuck?

One-point Hill Climbing can get stuck due to which of the following phenomenon? Local Maxima Inadmissible heuristic Ridges Plateau
1
vote
0answers
35 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
80 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 ...
3
votes
2answers
356 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
100 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
86 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 ...
1
vote
0answers
19 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
28 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
42 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
33 views

Is logistic regression used for unconstrained or constrained optimisation problems?

Is logistic regression used for unconstrained or constrained optimization problems, and why?
2
votes
1answer
65 views

Which algorithm can I use to solve a problem with multiple objectives and constraints?

Consider a problem with many objectives. In my case, these are school grades for different courses (or subjects). To be more concrete, suppose that my current grade for the math course is $12/20$ and ...
3
votes
1answer
798 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 ...