# Questions tagged [learning-rate]

For questions related to the concept of learning rate (of an optimization algorithm, such as gradient descent) in machine learning.

33 questions
Filter by
Sorted by
Tagged with
1 vote
27 views

### Do learning rate schedulers conflict with or prevent convergence of the Adam optimiser?

An article on https://spell.ml says Because Adam manages learning rates internally, it's incompatible with most learning rate schedulers. Anything more complicated than simple learning warmup and/or ...
• 11
70 views

### Is learning rate the only reason for training loss oscillation after few epochs?

Consider the following loss curve The x-axis is the no. of epochs and the y-axis is the loss function. You can observe that loss is decreasing drastically for the first few epochs and then starts ...
• 2,977
43 views

### GAN performance starts to get worse as training continues

I'm currently trying to train a GAN to recreate similar images from a dataset. The dataset is using the Eiffel Tower Pictures from Googles Quick Draw dataset. The images aren't very large (only 12x12 ...
189 views

### How does $\alpha$ affect the convergence of the TD algorithm?

In Temporal-Difference Learning, we update our value function by $V\left(S_{t}\right) \leftarrow V\left(S_{t}\right)+\alpha\left(R_{t+1}+\gamma V\left(S_{t+1}\right)-V\left(S_{t}\right)\right)$ If we ...
• 43
11 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 ...
80 views

### Commonly used learning rate schedules - linear warmup with linear decay?

I came across this post https://paperswithcode.com/methods/category/learning-rate-schedules which lists some different learning rate schedules and the number of papers which use them. I was a bit ...
• 746
36 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 ...
35 views

### How does the learning rate $\alpha$ vary in stationary and non-stationary environments?

In Sutton and Barto's book (Chapter 6: TD learning, 2nd edition), he mentions two ways of updating value function: Monte Carlo method: $V(S_t) \leftarrow V(S_t) + \alpha[G_t - V(S_t)]$. TD(0) method: ...
• 339
1 vote
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 ...
• 1,029
1 vote
38 views

### Why is the validation loss less than the training loss, and what can be said about the effect of the learning rate?

I have the following results I am trying to make sense of. I have attached the loss curves here for reference. As you can see, the first issue is that the validation loss is lower than the training ...
• 113
412 views

### Is there an ideal range of learning rate which always gives a good result almost in all problems?

I once read somewhere that there is a range of learning rate within which learning is optimal in almost all the cases, but I can't find any literature about it. All I could get is the following graph ...
• 178
1 vote
58 views

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 ...
• 11
1 vote
82 views

### If $\alpha$ decreases over time, why is Q-learning guaranteed to converge?

Q-Learning is guaranteed to converge if $\alpha$ decreases over time. On page 161 of the RL book by Sutton and Barto, 2nd edition, section 8.1, they write that Dyna-Q is guaranteed to converge if each ...
• 567
74 views

### Is stable learning preferable to jumps in accuracy/loss

A stable/smooth learning validation curve often seems to keep improving over more epochs than an unstable learning curve. My intuition is that dropping the learning rate and increasing the patience of ...
• 141
1k 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 ...
• 1,324
1 vote
44 views

### Is it a good idea to change the learning rate at each training step as a function of the loss?

Is it a good idea to change the learning rate at each training step as a function of the loss? i.e. for points with high loss value, put a high learning rate and for low loss value a low learning rate ...
53 views

### Would a different learning rate for every neuron and layer mitigate or solve the vanishing gradient problem?

I'm interested in using the sigmoid (or tanh) activation function instead of RELU. I'm aware of RELU advantages on faster computation and no vanishing gradient problem. But about vanishing gradient, ...
1 vote
102 views

### Why would the learning rate curve go backwards?

I'm working on recognizing the numbers 3 and 7 using the MNIST data set. I'm using cnn_learner() function from fastai library. When I plotted the learning rate, the ...
• 121
1 vote
67 views

### How can a learning rate that is too large cause the output of the network (and the error) to go to infinity?

It happened to my neural network, when I use a learning rate of <0.2 everything works fine, but when I try something above 0.4 I start getting "nan" errors because the output of my ...
77 views

### Why does learning rate reduce train-test generalization gap?

In this blog post: http://www.argmin.net/2016/04/18/bottoming-out/ Prof Recht shows two plots: He says one of the reasons the plot below has a lower train-test gap is because that model was trained ...
• 530
1 vote
33 views

### What is the equation of the learning rate decay in the Adam optimiser?

Adam is known as an algorithm that has an adaptive learning rate for each parameter. I believe this is due to the division by the term $$v_t = \beta_2 \cdot v_{t-1} + (1-\beta_2) \cdot g_t^2$$ Hence, ...
• 1,201
1 vote
61 views

### Is it harmful to set the learning rate of training a model to be too high if there is some decay function for the learning rate?

It is known that if $\alpha$ is set to high, then the cost function of the model may not converge. However, would a decaying of the learning rate provide some "tuning" of the $\alpha$ value during ...
• 1,201
1 vote
114 views

### How to best make use of learning rate scheduling in reinforcement learning?

How to best make use of learning rate scheduling in reinforcement learning? To me, a low learning rate towards the end to fine-tune what you've learned with subtle updates makes sense. But I don't ...
87 views

### Is it a good idea to overfit on a small part of your data for faster model convergence?

I working on a classification problem that needs to detect patterns on a time serie. Basically, there's a catch-all class that means "no pattern detected", the other are for the specific patterns. The ...
• 101
1 vote
223 views

• 395