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
13 views

Cover a surface with smaller predefined objects

I'm trying to make a program that takes a surface designed by the user, and different 3D geometries from a dataset as inputs and gives a good approximation of the surface using only the objects found ...
3
votes
1answer
48 views

What are the necessary mathematical properties to be a loss function in gradient based optimizations?

Loss functions are used in training neural networks. I am interested in knowing the mathematical properties that are necessary for a loss function to participate in gradient descent optimization. I ...
1
vote
0answers
11 views

What does the lambda parameter in the paper “Interpretable Explanations of Black Boxes by Meaningful Perturbation” do?

I do not understand the purpose of the $\lambda$ parameter in equation 3 of the paper Interpretable Explanations of Black Boxes by Meaningful Perturbation. $$m^{*}=\underset{m \in[0,1]^{\Lambda}}{\...
0
votes
2answers
32 views

Is “Pruning” only applicable to CNNs?

What Is Neural Network Pruning And Why Is It Important Today? The above article only talks about Convolutional Neural Networks: One of the first methods of pruning is pruning entire convolutional ...
2
votes
1answer
55 views

What gets optimized in convolutional neural network?

In a convolutional neural network, the hyperparameters such as number of kernels and stride, kernel size, etc are determined. After some combination of convolutions, ReLU and pooling layer there is ...
1
vote
1answer
70 views

In logistic regression, why is the binary cross-entropy loss function convex?

I am studying logistic regression for binary classification. The loss function used is cross-entropy. For a given input $x$, if our model outputs $\hat{y}$ instead of $y$, the loss is given by $$\text{...
0
votes
0answers
16 views

Gradient of Scalar objective cannot be efficiently calculated?

Suppose we generate the vector output $y$ from model $h(x, \theta)$, with input $x$ and parameters $\theta$. Reverse mode differentiation says that we can calculate the gradient \begin{align*} \...
0
votes
0answers
18 views

How to improve Face matching time

I'm working on a project that aims to detect each person's face while entering to a public space and store entering time and the person's image (array format) in Elasticsearch, and then detect each ...
7
votes
1answer
106 views

When should you not use the bias in a layer?

I'm not really that experienced with deep learning, and I've been looking at research code (mostly PyTorch) for deep neural networks, specifically GANs, and, in many cases, I see the authors setting <...
0
votes
0answers
33 views

Any RL approaches for this 2D space optimisation problem?

I have a list of rectangles, they are in certain order in 2D at the beginning. The task is to move them to get the boundary (rectangular) of the minimal area. It's OK to push off the dotted border as ...
0
votes
1answer
60 views

Use Reinforcement Learning instead of genetic algorithm for optimization

I want to use RL instead of genetic or any other evolutionary algorithm in order to find the best parameter for a function. Here is the problem: Given a function $$f(x,y,z,data)$$ x,y and z are some ...
1
vote
0answers
34 views

Optimizer that prevents parameters from oscillating

When we perform gradient descent, especially in an online setting where the training data is presented in a non-random order, a particular 1-dimensional parameter (such as an edge weight) may first ...
1
vote
0answers
28 views

What are some use cases of discrete optimization in Deep Learning?

When we talk of optimization, it usually boils down to gradient descent and its variants in the context of deep learning. However, I wonder if there are some works that use discrete optimization in ...
0
votes
0answers
35 views

What are the best optimizations I can add to my neural network?

I am making an artificial neural network from scratch (without nn libraries) in python. So, as you can guess, its extremely unoptimized and slow. For this neural ...
1
vote
1answer
69 views

How to avoid being stuck local optima in q-learning and q-network

When using Bellman equation to update q-table or train q-network to fit to greedy max values, the q-values very often get to the local optima and get stuck although randomisation rate ($\epsilon$) ...
1
vote
1answer
53 views

How to deal with evolutionary/genetic fitness function that can have both negative and positive values?

I am optimising function that can have both positive and negative values in pretty much unknown ranges, might be -100, 30, 0.001, or 4000, or -0.4 and I wonder how I can transform these results so I ...
4
votes
0answers
58 views

Why are most commonly used activation functions continuous?

I have come to notice that the most commonly used activation functions are continuous. Is there any specific reason behind this? Results such as this paper have worked on training networks with ...
1
vote
0answers
46 views

How can I model this problem as optimization problem that can be solved with ACO?

I have the following homework problem, where I need to explain how to model a certain problem as an optimization problem and how I can solve it with ACO. You have 6 portable media players $(P_i, ...
2
votes
0answers
23 views

Is it possible to ensure the convergence when training a RNN weight on its SVD decomposition?

I'm reading the following paper in which the author seems to do 2 things interesting: The hidden-to-hidden weight matrix of the RNN is SVD decomposed and train separately. Each orthogonal part of the ...
0
votes
1answer
50 views

How to make input variable as trainable parameter in a neural network?

I am working on an optimization problem. First, I have done forward training to work the network as a surrogate model, then I freeze the output and I want to find an optimal value of input for a given ...
1
vote
0answers
28 views

How to derive compact convex set K and its diameter D to program Accelegrad algorithm in practice?

Given the original paper (https://arxiv.org/pdf/1809.02864.pdf), I would like to implement the Accelegrad algorithm for which I report the pseudocode of the paper: In the pseudocode, the authors ...
0
votes
0answers
15 views

What do you keep in mind while defining a perturbation function for ILS algorithm?

I've been having troubles in defining the perturb function for the problem I am working on. I know that this function should help you in "jumping" to another "hill", but not so far ...
0
votes
0answers
20 views

What to do when Iterated Local Search (ILS) method keeps making the solution worse?

I've been trying to solve an optimization problem with ITERATED LOCAL SEARCH (ILS) method. I've generated the initial solution, then followed the steps of ILS. However, even after running the ...
2
votes
0answers
46 views

How does the support vector machine constraint imply that sample selection bias will not systematically affect the output of the optimisation?

I am currently studying the paper Learning and Evaluating Classifiers under Sample Selection Bias by Bianca Zadrozny. In section 3.4. Support vector machines, the author says the following: 3.4. ...
0
votes
0answers
64 views

What is the best algorithm for optimizing profit, rather than making predictions?

I am new to machine learning, so I am not sure which algorithms to look at for my business problem. Most of what I am seeing in tools like KNIME are geared toward making a prediction/classification, ...
0
votes
1answer
46 views

RMSprop equation - dividing by a matrix?

I've been trying to understand RMSprop for a long time, but there's something that keeps eluding me. $dW$ and $db$ are matrices (that's what I understand from the element-wise comment), so that must ...
1
vote
1answer
110 views

How are these equations of SGD with momentum equivalent?

I know this question may be so silly, but I can not prove it. In Stanford slide (page 17), they define the formula of SGD with momentum like this: $$ v_{t}=\rho v_{t-1}+\nabla f(x_{t-1}) \\ x_{t}=x_{...
1
vote
1answer
34 views

Why is Adam trapped in bad/suspicious local optima after the first few updates?

In the paper On the Variance of the Adaptive Learning Rate and Beyond, in section 2, the authors write To further analyze this phenomenon, we visualize the histogram of the absolute value of ...
2
votes
1answer
153 views

Why is second-order backpropagation useful?

Raul Rojas's book on Neural Networks dedicates section 8.4.3 to explaining how to do second-order backpropagation, that is, computing the Hessian of the error function with respect to two weights at a ...
1
vote
1answer
46 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 ...
1
vote
0answers
49 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
18 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 ...
8
votes
2answers
194 views

Why is the perceptron criterion function differentiable?

I'm reading chapter one of the book called Neural Networks and Deep Learning from Aggarwal. In section 1.2.1.1 of the book, I'm learning about the perceptron. One thing that book says is, if we use ...
2
votes
0answers
34 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
44 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
15 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
27 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 ...
3
votes
1answer
82 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
28 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
124 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
57 views

Why does Simulated Annealing not take worse solution if the energy difference becomes higher?

In Simulated 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? This means that, ...
1
vote
0answers
22 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
29 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
24 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
57 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
77 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
44 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
61 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
87 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
87 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 (...