Questions tagged [optimization]
For questions about implementing and improving optimization algorithms used in creating AI programs, or optimization in general.
210
questions
1
vote
0
answers
52
views
When can we unnest the minimizations/recursions in an value function(bellman optimality equation)?
When reading the following paper(page 4): An Approximate Dynamic Programming Approach
for Dual Stochastic Model Predictive Control
I could see that they were able to unnest the minimization's in the ...
- 11
0
votes
0
answers
15
views
Output Not Changing - Feeding Previous Outputs Back Into a Model
Full disclosure, I also posted this on Stack Overflow I have put a more theory based bent towards the question itself here
I have a simple model in pytorch based on the quickstart except instead of a ...
- 1
0
votes
0
answers
26
views
Multi-Task VAE, Decoder Activation Functions?
I'm working on a Multi-Task VAE with one Encoder and two Decoders. The input consists of a vector with parameters which describe a design of a fluid system. The goal is to reconstruct the parameters ...
- 1
1
vote
0
answers
58
views
Is this a bandit problem or a MDP?
I am trying to understand if this problem can be casted both as a bandit problem as well as an MDP.
Lets assume that we are trying to optimize sales $y_t$ based on investments $x_{1, t}, x_{2, t}$ ...
- 53
2
votes
1
answer
59
views
How to train a sample weight model for another ML model?
I'm trying to train a ML model, however the predictability of the different samples varies, i.e. some samples are inherently much harder to predict/estimate than others. Poorer predictions for these ...
- 123
1
vote
1
answer
31
views
Applicability of Holland's Schema Theorem to Genetic Algorithms with Non-Binary Individual Representations
I'm currently working on a problem formulation that requires non-binary individual representations in a genetic algorithm (GA). I've been exploring Holland's Schema Theorem as a theoretical basis for ...
- 11
0
votes
0
answers
23
views
Implementing momentum is causing calculation exceptions/errors
I am developing my own neural network in order to learn about how they work. I am implementing via C++ and the Eigen library (for matrix multiplication). I have a working implementation that seems to ...
1
vote
2
answers
86
views
Maximize a scoring function within the latent space of a generative model
Given a generative model, G, trained on a dataset D. This generative model can be either GAN or Diffusion based. Supposed each sample, x_i, generated by G, can be evaluated by a readily available ...
- 81
0
votes
1
answer
39
views
Best way to generate fitness landscape when using higher dimensional data
I'm using a GA to find the best set of parameters to maximize a fitness function. I want to draw a fitness landscape to visualize the effectiveness of the algorithm. The fitness function, calculated ...
0
votes
0
answers
15
views
What do I need to learn to tackle the following problem: make a program that optimizes decisions in the game PlateUp!
So, recently my friends and I have been hooked on a videogame called PlateUp!. The game is kind of a management game where the objective is to succesfully run a restaurant. The game can be roughly ...
0
votes
0
answers
14
views
Finding an optimal action score function for Multi-Armed Bandit Problem
Considering a multi-armed bandit problem where there are :
...
1
vote
0
answers
54
views
How does Openai's CLIP avoids dimensional collapse?
According to this paper from FAIR : https://arxiv.org/abs/2110.09348 , contrastive learning methods suffer from the problem of dimensional collapse where "the embedding vectors end up
spanning a ...
- 31
1
vote
1
answer
58
views
Cheap differentiable similarity metrics of vectors
I am looking to compute the similarity between a large set of vectors during neural network training - a process that is considerably expensive when choosing the wrong metric. So far, I am making use ...
1
vote
1
answer
58
views
Why are the non-linear activations in deep nets not learned?
Why can we not parametrize and learn the non-linear activations? For example, if we look at leaky ReLu which equals to $f(y)=y$ for $y>0$ and $f(y)=\alpha y$ for $y<0$, it seems that we can ...
- 639
0
votes
0
answers
36
views
Behaviour of PPO/similar Algos under action penalties
I am currently experimenting with PPO in different environments. I am interested in learning policies that fulfill a certain goal while keeping a specific value low. Here's an example:
Using PPO on a ...
0
votes
1
answer
54
views
Poor convergence of a neural network, which implements NMF
I'd like to understand why this simple network fails to converge. The resulting MSE error is an order of 10^4 - 10^5 bigger than what could be achieved. The task is to do a non-negative matrix ...
- 737
1
vote
1
answer
59
views
Optimizing a blackbox function with binary states
I have a non-linear black box function, which inputs a vector(size=250) and outputs a scalar value; f(x) = value.
The x variable is a vector of size 250 and has ...
- 111
0
votes
0
answers
39
views
Very high dimensional optimization with large budget, requiring high quality solutions
What would be theoretically the best performing optimization algorithm(s) in this case?
Very high dimensional problem: 250-500 parameters
Goal is to obtain very high quality solutions, not just "...
1
vote
0
answers
123
views
How to estimate the gradient of an argmin loss
Suppose we have a neural network $f_\theta(x)$, where $x$ is the input and $\theta$ is the network's parameters.
For each $\theta$, we can minimize $f_\theta(x)$ w.r.t. $x$ and obtain the minimum ...
- 111
0
votes
1
answer
74
views
How to speed up my neural network?
I would like to train an LSTM-based variational autoencoder on a large dataset (37 million sentences). However, I have calculated that my training speed as of now is too slow (on Google Colab). I am ...
0
votes
0
answers
35
views
What loss function should I use to penalize shift properly
I'm trying to fit a set of parameters $\mathbf{p} \in \mathbb{R}^P$ to a 1D function $\hat{f}(t)$ (e.g. waveform, time-series) where $t\in\mathbb{R}$ is the time coordinate of the signal $\hat{f}\in\...
- 111
0
votes
0
answers
25
views
How is model training affected after randomizing the weights of an intermediate layer of a pre-trained model?
Assuming that I have a deep learning model (let's say a ResNet) pretrained on a given dataset (let's say it is ImageNet). I load that model and randomize the weights of one of the intermediate layers, ...
1
vote
1
answer
298
views
How to determine if a decision tree is the (globally) optimal tree?
BACKGROUND: When constructing decision trees, the features are selected at various nodes based on whether it optimally splits the samples at that level (i.e., locally) using some user-chosen metric ...
- 922
1
vote
0
answers
75
views
What would be a good optimization technique for this kind of problem?
Problem Description:
Since I am not sure if there is a scientific term that categorizes this problem, I will do my best to describe it thoroughly.
Suppose there is a chamber that's being filled with ...
- 111
0
votes
1
answer
26
views
What are your "current parameters" in Minibatch Stochastic Gradient Descent?
I was reading a book on Deep Learning when I came across a line, more like a few words that didn't make apparent sense.
Thus, we will often settle for sampling a random minibatch of examples every ...
- 101
0
votes
1
answer
241
views
How to define a fitness function to make sure the best fitness value is 'close to 9' in genetic algorithm
I am learning about genetic algorithms (GA), but I encountered a question about the definition of the fitness function used in GA.
I understand that the fitness function should return a scalar value (...
- 1
0
votes
0
answers
102
views
The Small Set Expansion Hypothesis, this problem was solved or is open problem yet?
I found this problem by article called "Ten Lectures and Forty-Two Open Problems in the Mathematics of Data Science" published at 2016. I`m looking for an open problem at Data Science or/and ...
2
votes
1
answer
117
views
Multi-objective training involving maximization of one loss function and minimization of another
I need my model to predict $s$ from my data $x$. Additionally, I need the model to not use signals in $x$ that are predictive of a separate target $a$. My approach is to transform $x$ into a ...
- 121
1
vote
0
answers
241
views
Alternatives to Bayesian optimization
I am given a dataset $\mathcal{D} = \{\mathbf{x}_i\}_{i=1}^n$ and I need to find the point (in my case a material) $\mathbf{x}^*$ that maximizes a property $y$ (which can be obtained from a black-box ...
- 150
1
vote
1
answer
205
views
Why do we use gradient descent to minimize the loss function?
The purpose of training neural networks is to minimize a loss function, in this process we usually use gradient descent method.
But in Calculus, if we want to find the global minimum of a ...
- 111
1
vote
0
answers
41
views
Do NNs suffer from lack of efficiency in network structure and suggesting training parameters?
I am working on dynamical systems using Optimal Control theory and trying to find the connection between this field and Machine Learning. Consider a simple 2-layer Neural Network (NN) where the ...
2
votes
0
answers
28
views
How to create a loss function that penalizes duplicate indices in the output tensor?
We're working on a sequence-to-sequence problem using pytorch, and are using cross-entropy to calculate the loss when comparing the output sequence to the target sequence. This works fine and ...
- 121
1
vote
1
answer
527
views
How does MAML inner loop optimization works?
I started to learn meta-learning, reading the MAML paper https://arxiv.org/pdf/1703.03400.pdf
In the inner loop, I am calculating adapted parameters for each task, I will be doing multiple steps of ...
- 43
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 ...
- 1
1
vote
0
answers
36
views
Structured policies in dynamic programming: solving a toy example
I am trying to solve a dynamic programming toy example. Here is the prompt: imagine you arrive in a new city for $N$ days and every night need to pick a restaurant to get dinner at. The qualities of ...
- 11
1
vote
0
answers
149
views
Best algorithm for the Word Ladder puzzle
What would be the best performing algorithm to solve the Word Ladder problem, in terms of guaranteed finding of the shortest solution in the shortest possible time? Is it BFS, DFS, A*, IDA* or another ...
- 11
3
votes
1
answer
99
views
Why does my regression-NN completely fail to predict some points?
I would like to train a NN in order to approximate an unknown function $y = f(x_1,x_2)$. I have a lot of measurements $y = [y_1,\dots,y_K]$ (with K that could be in the range of 10-100 thousands) ...
- 31
1
vote
1
answer
31
views
Additional Optimizations for Convolutional Models On Inferencing
I am aware of several ways to optimize a convolutional (or any) model after training to make inferencing quicker. I am currently implementing BatchNormalization Folding and removing Dropout layers ...
- 113
-2
votes
2
answers
109
views
What does it mean by Generalization? [closed]
Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning
What does it mean by Generalization in this article?
- 299
0
votes
1
answer
47
views
Are Problems in AI Usually "Ill Posed"?
I was reading the following link (https://en.wikipedia.org/wiki/Well-posed_problem) on "Well Posed Problems". Supposedly, if a problem is "Well Posed", it must meet the following ...
- 269
1
vote
0
answers
82
views
Are Bayesian Optimization Methods Better Suited Noisy Optimization Problems?
We know that in many applied contexts (e.g. Machine Learning, Loss Functions for Neural Networks), the functions we are trying to optimize are "noisy" by definition (unlike in the classical ...
- 269
1
vote
2
answers
2k
views
Effects of ReLU Activation on Convexity of Loss Functions
I have heard the following argument being made regarding Neural Networks:
A Neural Network is a composition of several Activation Functions
Sigmoid Activation Functions are Non-Convex Functions
The ...
- 269
0
votes
0
answers
44
views
What I Should Do to Reduce Solution Size for Simulated Annealing Algorithm?
I am trying to find the best solution for radar placement problem with using multi objective simulated annealing algorithm.
So there is an area (in real map) and I want to put minimum count of radar ...
1
vote
0
answers
210
views
Why does the schema theorem of genetic algorithms hold?
I have been reading about the Schema Theorem - one of the first theorems from the field of evolutionary computing and genetic algorithms, largely responsible for justifying the use of genetic ...
- 269
2
votes
2
answers
100
views
Does reaching the global optima guarantee good performance in a task?
It is to my understanding that, in deep learning, we are essentially trying to minimize the loss function that we have defined and reach its global optima through some form of optimization technique. ...
- 153
0
votes
0
answers
83
views
Is it possible to find a good neural network structure without training it? [duplicate]
Neural networks consist of so many parameters. Researchers could create as many possible neural networks as they wish. So I want to ask a general question. Could we devise an evolutionary algorithm ...
- 173
1
vote
0
answers
77
views
a loss for binary step function data
I have some data with ground truth that looks like a binary step function, where part of it is 0 and part is one.
An example for the GT can be like ...
- 111
0
votes
0
answers
113
views
Why is there a Hessian diagonal approximation? And when can we use it?
This topic has been introduced in "Pattern Recognition and Machine Learning, Bishop, 2006", section 5.4.1. I am a bit confused about this method and I have two questions.
Why this method ...
2
votes
1
answer
249
views
How do I use machine learning to create an optimization algorithm?
Let's say that I want to create an optimization algorithm, which is supposed to find an optimum value for a given objective function. Creating an optimization algorithm to explore through the search ...
- 23
0
votes
0
answers
30
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 ...
- 1