Questions tagged [hyperparameter-optimization]

For questions related to the concept of hyper-parameter optimization, that is, the task of finding the best hyper-parameters for a particular learning algorithm (e.g. gradient descent) or model (e.g. a multi-layer neural network) using an optimization method (e.g. Bayesian optimization or genetic algorithms).

Filter by
Sorted by
Tagged with
2
votes
1answer
38 views

Is it possible to train one part of the network with a particular learning rate and the other part with a different one?

I have a combined network consisting of two parts: one is for images and the other is for numerical data. Each sample is matched with a numerical case by an ID. For this combined network, a ...
4
votes
1answer
55 views

Bayesian hyperparameter optimization, is it worth it?

In the Deep Learning book by Goodfellow et al., section 11.4.5 (p. 438), the following claims can be found: Currently, we cannot unambiguously recommend Bayesian hyperparameter optimization as an ...
2
votes
1answer
56 views

What should the value of epsilon be in the Q-learning?

I am trying to understand Reinforcement Learning and already explored different Youtube videos, blog posts, and Wikipedia articles. What I don't understand is the impact of $\epsilon$. What value ...
1
vote
1answer
44 views

What is the impact of changing the crossover and mutation rates?

What is the impact of using a: low crossover rate high crossover rate low mutation rate high mutation rate
1
vote
0answers
43 views

Why does PPO lead to a worse performance than TRPO in the same task?

I am training an agent with an Actor-Critic network and update it with TRPO so far. Now, I tried out PPO and the results are drastically different and bad. I only changed from TRPO to PPO, the rest of ...
1
vote
0answers
28 views

How should I change the hyper-parameters of the C51 algorithm, in order to obtain higher reward?

I have a scenario where, in an ideal situation, the greedy approach is the best, but when non-idealities are introduced which can be learned, DQN starts doing better. So, after checking what DQN ...
1
vote
1answer
25 views

What is the difference between sensitivity analysis and parameter tuning?

I tried different values of genetic algorithm operators: many crossover rates from 20% to 80% many crossover rates from 1% to 20% varying the population size The study of different parameter values ...
0
votes
0answers
51 views

How to determine the number of fully connected layers for a convolutional neural network?

How many fully connected layers should be added to a convolutional neural network? Does it depend on input size to the fully connected layer? If so, how do we decide? What if the input size of the ...
1
vote
2answers
47 views

Why is an embedding of dimension 400 enough to represent 70000 words?

I am learning PyTorch on Udacity. In lesson 8, section 11: Training the Model, the instructor writes: Then I have my embedding and hidden dimension. The embedding dimension is just a smaller ...
1
vote
0answers
37 views

Unable to meet desired mean squared error

I wish to get MSE < 0.5 on test data (https://easyupload.io/zr7xf3) which is 20% of given data chosen randomly. But I am reaching 0.73 using both plain Ridge Regression as well as a neural network ...
0
votes
0answers
27 views

How to optimize my GAN generator and discriminator models' structures?

I'm using Tensorflow to feed a DCGAN 3000 320x320 colored images of cars. The goal is to generate new cars. I've been training on Google Colab for the past 10 hours or so. I guess I can expect results ...
0
votes
0answers
49 views

Rules of thumb for hidden layer sizes [duplicate]

I am quite new to neural networks, and would like to save myself some of the learning curve by having some rules of thumb about hidden layer sizes. I would also like to have a rule of thumb for the ...
4
votes
2answers
225 views

What is the meaning of “exploration” in reinforcement and supervised learning?

While exploration is an integral part of reinforcement learning (RL), it does not pertain to supervised learning (SL) since the latter is already provided with the data set from the start. That said, ...
0
votes
0answers
21 views

Reward and loss follow the same shape in DQN

If the accumulated reward increases, the loss increases and vice versa. This is a strange behaviour. See the figure below for an example. What is the possibility of having this behaviour in DQN? I ...
0
votes
1answer
83 views

What is the best activation function for the embedding layer in a deep auto-encoder?

I am designing a deep autoencoder for graph embedding (exactly node embedding) following this paper SDNE. In the original paper, they used the sigmoid activation for all hidden layers in the ...
1
vote
1answer
67 views

How to determine the number of hidden layers and units of a deep auto-encoder?

I am using a deep autoencoder for my problem. However, the way I choose the number of hidden layers and hidden units in a hidden layer is still based on my feeling. The size of the model that ...
3
votes
1answer
175 views

How should I choose the target's update frequency in DQN?

I have been dealing with a problem that I'm trying to solve with DQN. A general question that I have is regarding the target's update frequency. How should it change? Depending on what factor do we ...
1
vote
0answers
21 views

Best/quickest approach for tuning the hyperparameters of a restricted boltzmann machine

I have an RBM model which takes extremely long to train and evaluate because of the large number of free parameters and the large amount of input data. What would be the most efficient way of tuning ...
3
votes
1answer
60 views

How are training hyperparameters determined for large models?

When training a relatively small DL model, which takes several hours to train, I typically start with some starting points from literature and then use a trial-and-error or grid-search approach to ...
0
votes
1answer
47 views

96.91% accuracy on MNIST after 2 hours of training using custom made neural net library. Ways to improve?

I wanted to understand back-propagation so I made a basic neural network library. I used momentum, with learning rate = $0.1$, beta = $0.99$, epochs = $200$, batch size = $10$, loss function is cross ...
0
votes
1answer
143 views

Why is my Soft Actor-Critic's policy and value function losses not converging?

I'm trying to implement a soft actor-critic algorithm for financial data (stock prices), but I have trouble with losses: no matter what combination of hyper-parameters I enter, they are not converging,...
2
votes
0answers
25 views

Deriving hyperparameter updates in Online Interactive Collaborative Filtering

I've been going through "Online Interactive Collaborative Filtering Using Multi-Armed Bandit with Dependent Arms" by Wang et al. and am unable to understand how the update equations for the ...
1
vote
0answers
36 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 ...
0
votes
0answers
138 views

How to choose hyperparameters in double DQN?

I'm looking for some indications about the tuning of hyper-parameters in building my double DQN. I have a time series problem (with about 2000 observations and no terminal state, I have to max the ...
1
vote
0answers
36 views

How do we choose the filters for the convolutional layer of a convolution neural network?

Since the hidden layers of a CNN work as a trainable feature extractor, more detailed content based on a larger number of pixels shall require bigger filter sizes. But for cases where localized ...
1
vote
0answers
32 views

Should we start with a small batch-size and increase during training to improve sample efficiency?

Just made an interesting observation playing around with the stable-baseline's implementation of PPO and the BipedalWalker environment from OpenAI's Gym. But I believe this should be a general ...
0
votes
2answers
41 views

Is it theoretically possible (or impossible) that principal component analysis worsens the performance of the model?

In case I had a prediction model and decided to add a PCA step prior to the model, is it theoretically possible/impossible that the number of output dimensions that is better for all tests may perform ...
0
votes
0answers
21 views

Larger neural network with almost similar training and validation error as smaller network

I am building a neural network that takes as input 202 units and outputs a 200 dimension continuous variable. While trying to find the best model, one of the parameters i tune is the the number of ...
1
vote
1answer
35 views

How to know if the hyperparameters of a neural network relate to each other?

According this thread some hyperparameters are independent from each other while some are directly related. One of the answers give an example where two hyperparameters affect each other. For ...
1
vote
2answers
82 views

How is a validation set used to tune the hyperparameters in a non-biased way, if the new models depends on the values of these?

I've built a neural network from the scratch, choosing arbitrary numbers for the hyperparameters: learning rate, number of hidden layers and neurons for these, number of epochs and size of mini ...
2
votes
1answer
52 views

After having selected the best model with cross-validation, for how long should I train it?

When using k-fold cross-validation in a deep learning problem, after you have computed your hyper-parameters, how do you decide how long to train your final model? My understanding is that, after the ...
1
vote
0answers
57 views

Why can't I Hyper tune my KNNBasic Algorithm?

I've been trying to hyper tuning my KNNBasic algorithm by the help of grid search for recommendation system for movie review data. The problem is that both of my KNNBasicTuned and KNNBasicUntuned ...
4
votes
2answers
114 views

Why do we need both the validation set and test set?

I know that this has been asked a hundred times before, however, I was not able to find a question (and an answer) which actually answered what I wanted to know, respectively, which explained it in a ...
3
votes
0answers
83 views

Are there principled ways of tuning a neural network in case of overfitting and underfitting?

Whenever I tune my neural network, I usually take the common approach of defining some layers with some neurons. If it overfits, I reduce the layers, neurons, add dropout, utilize regularisation. ...
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
0answers
21 views

When stacking LSTM's, should the hidden units increase?

I'm using Weights and Biases to do some hyperparameter sweeping for a supervised sequence-to-sequence problem I'm working on. One thing I noticed is that the sweeps with a gradually increasing number ...
1
vote
1answer
77 views

How to fairly conduct a model performance with 5-fold cross validation after augmentation?

I have, say, a (balanced) data-set with 2k images for binary classification. What I have done is that randomly divided the data-set into 5 folds; copy-pasted all 5-fold data-set to have 5 exact ...
1
vote
0answers
37 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 ...
4
votes
1answer
96 views

Is there a reason to choose regular momentum over Nesterov momentum for neural networks?

I've been reading about Nesterov momentum from here and it seems like a nice improvement over regular momentum with no extra cost whatsoever. However, is this really the case? Are there instances ...
2
votes
1answer
106 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 ...
4
votes
0answers
40 views

What are some ways to quickly evaluate the potential of a given NN architecture?

Main question Is there some way we can leverage general knowledge of how certain hyperparameters affect performance, to very rapidly get some sort of estimate for how good a given architecture could ...
3
votes
0answers
22 views

Is it normal to see oscillations in tested hyperparameters during bayesian optimisation?

I've been trying out bayesian hyperparameter optimisation (with TPE) on a simple CNN applied to the MNIST handwritten digit dataset. I noticed that over iterations of the optimisation loop, the tested ...
3
votes
0answers
46 views

How can I do hyperparameter optimization for a CNN-LSTM neural network?

I have built a CNN-LSTM neural network with 2 inputs and 2 outputs in Keras. I trained the network with model.fit_generator() (and not ...
1
vote
0answers
33 views

Hyperparameter optimisation over entire range or shorter range of training episodes in Deep Reinforcement Learning

I am optimising hyperparameters for my deep reinforcement learning project (using PPO2, DQN and A2C) and was wondering: Should I find the optimum hyperparameters to get maximum reward from training ...
3
votes
0answers
20 views

How to organize model training hyperparameters

I am working on multiple deep learning projects, most of them in the area of computer vision. For many of them I create multiple models, try different approaches, use various model architectures. And ...
3
votes
2answers
2k views

What is a “surrogate model”?

In the following paragraph from the book Automated Machine Learning: Methods, Systems, Challenges (by Frank Hutter et al.) In this section we first give a brief introduction to Bayesian ...
6
votes
1answer
1k views

Is this idea to calculate the required number of hidden neurons for a single hidden layer neural network correct?

I have an idea to find the optimal number of hidden neurons required in a neural network, but I'm not sure how accurate it is. Assuming that it has only 1 hidden layer, it is a classification problem ...
5
votes
1answer
98 views

How can I avoid overfitting when doing parameter tuning?

I very often applied a grid search to tune the parameters of my supervised model. I have the feeling that parameter tuning will eventually (very often) lead to overfitting? Is this crazy to say? Is ...
14
votes
1answer
148 views

Will parameter sweeping on one split of data followed by cross validation discover the right hyperparameters?

Let's call our dataset splits train/test/evaluate. We're in a situation where we require months of data. So we prefer to use the evaluation dataset as infrequently as possible to avoid polluting our ...
5
votes
1answer
47 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 ...