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
0
votes
0answers
20 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
27 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
212 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
19 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
32 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
45 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
53 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
19 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 ...
2
votes
1answer
54 views

How are training hyperparameters determined for large models?

When training relatively small DL model which takes several hours to train, I typically start with some starting points from literature and then use trial-and-error or grid-search approach to tune up ...
0
votes
1answer
45 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
87 views

Soft Actor Critic - Losses are not converging

I'm trying to implement soft actor-critic algorithm for financial data (stock prices) and I have trouble with losses, no matter what combination of HyperParameters 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
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 ...
1
vote
0answers
34 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
31 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
38 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
30 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
31 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
51 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
50 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
107 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
80 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
0answers
55 views

Why do momentum techniques not work well for RNNs?

AFAIK, momentum is quite useful when training CNNs, and can speed-up the training substantially without any drop in validation accuracy. I've recently learned that it is not as helpful for RNNs ...
1
vote
3answers
1k 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
73 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
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 ...
4
votes
1answer
81 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
72 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 ...
3
votes
0answers
39 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 ...
2
votes
0answers
20 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
40 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
31 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
1k 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 ...
5
votes
1answer
73 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 ...
1
vote
1answer
53 views

How to use a deep learning network on new data-set?

I am trying to use a network for classification. This network works very well on the author's example data, but doesn't work on new data. Currently, I am using the popular EEG Motor Movement/Imagery ...
5
votes
1answer
44 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 ...
1
vote
0answers
158 views

Threshold selection for Siamese network hyper-parameter tuning

I'm interested in modeling a Siamese network for facial verification. I've already written a simple working model that inputs feature vectors generated from two CNNs with shared weights then outputs a ...
1
vote
0answers
21 views

Improving Recall of a Certain Class

Let's say that we have a test data set with $20,000$ observations for which we want to make a binary prediction for. When we apply our best trained model to this data set (e.g. logistic regression ...
4
votes
1answer
180 views

An intuitive explanation of Adagrad, its purpose and its formula

It (Adagrad) adapts the learning rate to the parameters, performing smaller updates (i.e. low learning rates) for parameters associated with frequently occurring features, and larger updates (i.e. ...
4
votes
1answer
128 views

What is the best measure against overfitting?

I wanted to ask about the methodology of testing the ML models against overfitting. Please note that I don't mean any overfitting reducing methods like regularisation, just a measure to judge whether ...
1
vote
0answers
35 views

How do you scale your ML problems?

While I have limited resource usually to train my machine learning models, I often find that my hyperparameter optimization procedure is not necessary using all my GPU and CPU, and that is because the ...
2
votes
2answers
53 views

Does this hyperparameter optimisation approach yield the optimal hyperparameters?

Say I have a ML model which is not very costly to train. It has around say 5 hyperparameters. One way to select best hyperparameters would be to keep all the other hyperparamaters fixed and train ...
2
votes
1answer
77 views

Can we automate the choice of the hyper-parameters of the evolutionary algorithms?

Certain hyper-parameters (e.g. the size of the offspring generation or the definition of the fitness function) and the design (e.g. how the mutation is performed) of evolutionary algorithms usually ...
1
vote
0answers
67 views

Why doesnt my lstm model for time series prediction improve after certain level of performance?

I created an lstm model which predicts multioutput sequeances. It takes variable length sequences as input. These sequences are padded with zero to obtain equal length. Note that the time series are ...
0
votes
1answer
46 views

Evolving Machine Learning [closed]

It seems to me that, right now, the key to making a good Machine Learning model is in choosing the right combination of hyper-parameters. Firstly: Am I right in saying, if a model is able to tune it'...
1
vote
0answers
70 views

How to use TensorFlow with hyperparameter tuning to optimize parameters for a robot simulator

I am trying to implement a DNN to optimize a set of 7 parameters that are used in a robot swarm simulator on the ARGoS platform. the program is a compiled C++ executable that reads the parameters from ...
5
votes
3answers
211 views

How is neural architecture search performed?

I have come across something that IBM offers called neural Architecture search. You feed it a data set and it outputs an initial neural Architecture that you can train. How is neural architecture ...