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
3 votes
0 answers
23 views

How should I compare multiple machine learning models to be (generally) fair to all models?

I am testing multiple models on IBM HR Analytics Attrition Dataset (1470 lines) and HR Analytics dataset (15000 lines) for a research project. The models include traditional models (Naive Bayes, SVM), ...
user avatar
0 votes
0 answers
11 views

Finding "look_back" & "look_ahead" hyper-parameters for Seq2Seq models

For Seq2Seq deep learning architectures, viz., LSTM/GRU and multivariate, multistep time series forecasting, it is important to convert the data to a 3D dimension: (batch_size, look_back, ...
user avatar
  • 183
2 votes
3 answers
164 views

Is it possible to learn the number of layers?

Is it possible, in a transformer or other deep architecture, to include the number of layers as a parameter of the model so it could be learned? In fact, I have a keras layer that I use to change the ...
user avatar
  • 51
0 votes
0 answers
11 views

What is a good first guess to set hyper parameters for Adam optimiser for Faster RCNN?

Is there a way to make an educated guess on how to set the hyper parameters for Adam optimiser for Faster RCNN depending on the size of the dataset and the loss function? I use the default values for ...
user avatar
0 votes
0 answers
27 views

Resolving Derivation Discrepancies for Differentiating through Optimization Paths

I'm reading the paper "Optimizing Millions of Hyperparameters by Implicit Differentiation". The key contribution of the paper is to show that you can replace optimizing through the ...
user avatar
  • 1
3 votes
1 answer
69 views

How do I design the network for Deep Q-Network?

I am playing with deep q-learning and I am thinking about what the proper architecture of a network used for deep q-learning is. I have a very simple environment, basically a 18x18 matrix, where 3 ...
user avatar
  • 133
0 votes
0 answers
29 views

Should hyper-parameters used in the mutation operator be fixed or variable?

Let's say I have a function $f(p_{i,t})$ and want to optimize $p_{i,t}$ so that I minimize a certain loss. Here, $p_{i,t}$ is the individual $i$ at iteration $t$. Now, $p_{i,t}$ can live anywhere ...
user avatar
  • 179
0 votes
1 answer
33 views

How can I interpret the value returned by score(X) method of sklearn.neighbors.KernelDensity?

For sklearn.neighbors.KernelDensity, its score(X) method according to the sklearn KDE documentation says: Compute the log-...
user avatar
  • 183
1 vote
1 answer
90 views

How does stochastic gradient descent undo the normalization done by the batch normalization?

I want to understand the handshake between SGD (or mini-batch GD) and batch normalization. Below, an explanation quoted from this Medium article. However, I am confused about the denormalization by ...
user avatar
  • 13
0 votes
0 answers
38 views

How to identify clusters of best hyperparameters from noisy hyperparameter optimization?

I'd like to optimize the hyperparameters for a random forest model that is already somewhat time-consuming to train. With adding cross-validation and multiple hyperparameter combinations, I might be ...
user avatar
1 vote
1 answer
61 views

Random forests - are more estimators always better?

I'm learning about more advanced methods of hyperparameter optimization, such as the Bayesian methods in the scikit-optimize package. For those unfamiliar with the ...
user avatar
2 votes
1 answer
80 views

What components of reinforcement learning influence the result the most?

I'm working on my thesis concerning a reinforcement learning problem and am trying to prioritise my time on different components of it: Formalising the agent environment (like the design of state-, ...
user avatar
  • 85
0 votes
0 answers
21 views

Is there a way to adapt Particle Swarm Optimization to an incremental/online learning setting?

As stated in the title, is there a way to adapt PSO to an online scenario where new data samples arrive continuously? In more detail: suppose that I have a classifier with several parameters for which ...
user avatar
0 votes
1 answer
906 views

How to fine-tune GPT-J with small dataset

I have followed this guide as closely as possible: https://github.com/kingoflolz/mesh-transformer-jax I'm trying to fine-tune GPT-J with a small dataset of ~500 lines: ...
user avatar
5 votes
2 answers
702 views

Do we need automatic hyper-parameter tuning when we have a large enough dataset?

Hyperparameter tuning is the process of selecting the optimal hyperparameters for an ANN. Now, my guess is that, if we have sufficient data (say, 1.4 million for, say, 6 features), the model can be ...
user avatar
2 votes
1 answer
136 views

How do I choose the hyper-parameters for a model to detect different guitar chords?

I need to build a hand detector that recognizes the chord played by a hand on a guitar. I read this article Static Hand Gesture Recognition using Convolutional Neural Network with Data Augmentation ...
user avatar
  • 73
1 vote
0 answers
28 views

How do you decide that you have tested enough hyper-parameter combinations for a specific neural network architecture?

How do you decide that you have tested enough hyper-parameter combinations for a specific neural network architecture to discard it and move on to a new model? Do you have a structured (generic) ...
user avatar
  • 11
0 votes
0 answers
12 views

Loss & accuracy curves from learning rate range test interpretation

I am working on a project doing experiments with the Learning Rate Range Test (See "A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and ...
user avatar
2 votes
0 answers
38 views

Has the idea of using different learning rates for different layers been explored in the literature?

I wonder whether there are heuristic rules for the optimal selection of learning rates for different layers. I expect that there is no general recipe, but probably there are some choices that may be ...
user avatar
1 vote
1 answer
48 views

Can the optimal learning rate differ for different architectures?

In several courses and tutorials about neural networks, people often say that the learning rate (LR) should be the first hyper-parameter to be tuned before we tweak the others. For example, in this ...
user avatar
  • 1,039
1 vote
0 answers
52 views

Why doesn't anyone use reinforcement learning to find the best possible alternative to backpropagation?

To be clear, I'm very uninformed on the topic of alternative learning algorithms to backprop, all my knowledge comes from articles like these: lets-not-stop-at-backprop backprop-alternatives we-need-a-...
user avatar
  • 103
3 votes
2 answers
2k views

How to determine the embedding size?

When we are training a neural network, we are going to determine the embedding size to convert the categorical (in NLP, for instance) or continuous (in computer vision or voice) information to hidden ...
user avatar
0 votes
1 answer
128 views

Is it valid to implement hyper-parameter tuning and THEN cross-validation?

I have a multi-label classification task I am solving. I have done hyperparameter tuning (with Keras Tuner) to determine the best configuration for my neural network. Is it valid to do this (determine ...
user avatar
1 vote
1 answer
77 views

How many singular vectors do we need to calculate for SVD?

In the geometrical interpretation of SVD, the data points that we have need to be imagined as points in high dimensional space (say $d$-dimensional space). But we need to find a hyperplane in $k-$...
user avatar
  • 3,099
1 vote
0 answers
21 views

Are there guiding principles as to which activation functions suit a given RL algorithm?

Are there rules of thumb as to which activation functions work well (or which one would not) on the policy and value network of a class of RL algorithms? For hidden layers and for the output layer. ...
user avatar
  • 507
3 votes
2 answers
283 views

What are the best hyper-parameters to tune in reinforcement learning?

Obviously, this is somewhat subjective, but what hyper-parameters typically have the most significant impact on an RL agent's ability to learn? For example, the replay buffer size, learning rate, ...
user avatar
2 votes
0 answers
29 views

Is there an optimal number of species for NEAT?

Is there an optimal number of species for NEAT? Since too low and too high is bad, I am thinking about adjusting the threshold of the distance function at runtime in order to have the number of ...
user avatar
  • 51
1 vote
0 answers
37 views

Why does Adam optimizer work slower than Adagrad, Adadelta, and SGD for Neural Collaborative Filtering (NCF)?

I've been working on Neural Collaborative Filtering (NCF) recently to build a recommender system using Tensorflow Recommenders. Doing some hyperparameter tuning with different optimizers available in ...
user avatar
3 votes
1 answer
66 views

What is the most statistically acceptable method for tuning neural network hyperparameters on very small datasets?

Neural networks are usually evaluated by dividing a dataset into three splits: training, validation, and test The idea is that critical hyperparameters of the network such as the number of epochs ...
user avatar
  • 391
0 votes
2 answers
32 views

Do larger numbers of hidden layers have a bigger effect on a classification model's accuracy?

I trained different classification models using Keras with different numbers of hidden layers and the same number of neurons in each layer. What I found was the accuracy of the models decreased as the ...
user avatar
2 votes
0 answers
65 views

How to Select Model Parameters for Transformer (Heads, number of layers, etc)

Is there a general guideline on how the Transformer model parameters should be selected, or the range of these parameters that should be included in a hyperparameter sweep? Number of heads Number of ...
user avatar
0 votes
1 answer
234 views

What to do with a GAN that trained well but got worse over time?

I am training a WGAN-GP network based on the following paper, though I am using a different dataset. Now, for the first ~ 60-70 epochs, my network trained really well, which I could see in the loss ...
user avatar
2 votes
1 answer
55 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 ...
user avatar
4 votes
1 answer
98 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 ...
user avatar
2 votes
1 answer
794 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 ...
user avatar
2 votes
1 answer
134 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
user avatar
  • 131
1 vote
0 answers
196 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 ...
user avatar
  • 31
2 votes
1 answer
104 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 ...
user avatar
1 vote
1 answer
118 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 ...
user avatar
  • 131
1 vote
2 answers
178 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 ...
user avatar
  • 181
0 votes
0 answers
44 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 ...
user avatar
4 votes
2 answers
575 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, ...
user avatar
  • 167
1 vote
1 answer
929 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 ...
user avatar
1 vote
1 answer
412 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 ...
user avatar
3 votes
1 answer
1k 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 ...
user avatar
1 vote
0 answers
31 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 ...
user avatar
3 votes
1 answer
77 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 ...
user avatar
  • 133
0 votes
1 answer
86 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 ...
user avatar
  • 11
0 votes
1 answer
568 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,...
user avatar
  • 3
2 votes
0 answers
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 ...
user avatar