Questions tagged [optimization]

For questions about implementing and improving optimization algorithms used in creating AI programs, or optimization in general.

Filter by
Sorted by
Tagged with
0 votes
0 answers
21 views

Is GPU undervolting employed with powering AI models like chatgpt?

ChatGPT runs on thousands of GPUs that pull a lot of power and as a result, dissipate a lot of heat. This effectively makes the cost of powering the AI high in two aspects: power consumption Cooling ...
machine_1's user avatar
  • 133
1 vote
1 answer
28 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 ...
CES's user avatar
  • 11
0 votes
0 answers
21 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 ...
user1311627's user avatar
1 vote
2 answers
82 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 ...
terenceflow's user avatar
0 votes
1 answer
37 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 ...
program1232123's user avatar
0 votes
0 answers
13 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 ...
Francisco José Letterio's user avatar
0 votes
0 answers
13 views

Finding an optimal action score function for Multi-Armed Bandit Problem

Considering a multi-armed bandit problem where there are : ...
MohammadAli Zeraatkar's user avatar
1 vote
0 answers
33 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 ...
Souhaielrmx's user avatar
1 vote
1 answer
56 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 ...
postnubilaphoebus's user avatar
1 vote
1 answer
57 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 ...
Gilad Deutsch's user avatar
0 votes
0 answers
34 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 ...
Lukas Schroth's user avatar
0 votes
1 answer
43 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 ...
NikoNyrh's user avatar
  • 662
1 vote
1 answer
54 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 ...
oakca's user avatar
  • 111
0 votes
0 answers
37 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 "...
Charly Empereur-mot's user avatar
1 vote
0 answers
106 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 ...
Mingzhou Liu's user avatar
0 votes
1 answer
70 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 ...
postnubilaphoebus's user avatar
0 votes
0 answers
34 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\...
Firman's user avatar
  • 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, ...
Jefferson White's user avatar
2 votes
1 answer
241 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 ...
Snehal Patel's user avatar
0 votes
0 answers
8 views

How to perform prescriptive analysis with timeseries models (ARIMA / Prophet)?

We have recently come across a problem of applying prescriptive modeling techniques to time series models in a business analytics context. For the HR domain, we are using employees demographic data , ...
Shakeel raja's user avatar
1 vote
0 answers
74 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 ...
Sobhan's user avatar
  • 111
0 votes
0 answers
23 views

Generalize and optimize a model for multiple time series

I have a physics equation that takes so much time to be solved computationally. So the idea is to optimize this computational time with Machine Learning techniques. I've already generated data ...
giovasbr's user avatar
0 votes
0 answers
29 views

Is it possible or useful to perform quantization-aware training on an untrained model?

Having done some online searches on the topic of quantization, and more specifically, quantization-aware training, I have noticed that all guides and tutorials start by using a pre-trained model, or ...
Nathan.Eilisha Shiraini's user avatar
0 votes
0 answers
110 views

Optimal weight decay value in Adam

Is there any rule of thumb while assigning the weight_decay parameter in Adam optimizer? As in, is it somehow related to (smaller or larger than) the learning rate ...
helloworld's user avatar
0 votes
0 answers
11 views

Solutions for free-form bin packing?

I'm working on a solution for free-form bin packing and what I have found so far is https://www.researchgate.net/publication/267165843_A_scanline-based_algorithm_for_the_2D_free-...
Mulliquin's user avatar
0 votes
0 answers
9 views

How Problem Formulation affects Optimization and Local Optima

Suppose we are dealing with a categorical classification problem and have x number of categories. Usually the correct label is represented by a x-dimensional one hot vector. I'm wondering what happens ...
Snowball's user avatar
  • 215
0 votes
1 answer
24 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 ...
HarshDarji's user avatar
0 votes
1 answer
227 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 (...
DavidK's user avatar
  • 1
0 votes
0 answers
101 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 ...
Leonardo Teramatsu's user avatar
2 votes
1 answer
115 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 ...
ChargeShivers's user avatar
1 vote
0 answers
226 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 ...
ado sar's user avatar
  • 150
1 vote
1 answer
168 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 ...
Proton's user avatar
  • 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 ...
Mehdi Moghadasian's user avatar
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 ...
vgoklani's user avatar
  • 121
1 vote
1 answer
486 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 ...
Grumpy C's 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 ...
Decadz's user avatar
  • 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 ...
learningowl's user avatar
1 vote
0 answers
141 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 ...
Bill Kavvas's user avatar
3 votes
1 answer
95 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) ...
MttRch's user avatar
  • 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 ...
theastronomist's user avatar
-2 votes
2 answers
102 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?
user366312's user avatar
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 ...
stats_noob's user avatar
1 vote
0 answers
80 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 ...
stats_noob's user avatar
1 vote
2 answers
1k 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 ...
stats_noob's user avatar
0 votes
0 answers
41 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 ...
TarabydaVllasıCafcaflıAtArabsı's user avatar
1 vote
0 answers
202 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 ...
stats_noob's user avatar
2 votes
2 answers
98 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. ...
tangolin's user avatar
  • 153
0 votes
0 answers
82 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 ...
bitWise's user avatar
  • 173
1 vote
0 answers
73 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 ...
Alex's user avatar
  • 111
0 votes
0 answers
102 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 ...
Hossein Aghamohammadi's user avatar

1
2 3 4 5