Questions tagged [generalization]

The tag has no usage guidance.

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

Good training/test results, but very poor performance in inference as the stream data is coming

I am interested in the audio classification problem. After labeling the audio recordings I have in Praat software environment, I extract the MFCC features from each labeled frame and create an SVM ...
Yalçın Cenik's user avatar
0 votes
0 answers
5 views

How Can I Train a Real-World-Ready Classifier with Limited Real Data and Abundant Open-Source Data?

I am trying to train a text classifier with open-source data to generalize on the real user traffic (henceforth "real data"). However, even though I have many annotated open-source data, I ...
Mr.Robot's user avatar
  • 217
0 votes
0 answers
6 views

Using validation data in optimization scenarios e.g. with genetic algorithms

I'm not too familiar with optimization algorithms e.g. genetic algorithms and I'm wondering whether it makes sense to employ a validation set in this context similarly to when we train a supervised ...
James Arten's user avatar
8 votes
6 answers
916 views

Confused about the notion of overfitting and noisy target function

So I am reading a textbook called "Learning from Data" by Abu Mostafa et al. I am confused about the following concepts: According to the authors, most real-world target functions $f$ are ...
Fraïssé's user avatar
  • 1,520
2 votes
1 answer
21 views

Sample size Red flags for a data set I was asked to analyze, please help

I am working in polishing up work an undergraduate class did and the data set is raising a lot of red flags for me. Like to the point that if these concerns I have aren’t resolved by either redoing ...
JewJitsu11B's user avatar
0 votes
0 answers
9 views

Aggregate predictions to generalize on large scale

I actually work on medical datas to predict outcome after treatment on patients with metastasis lesions of carcinomas. Each patient have different number of lesions with some with like 30 lesions and ...
Nicolas's user avatar
  • 13
0 votes
0 answers
12 views

Does generalization methods in ANN increase variance in results?

I am new to generalization techniques in machine learning and I have been experimenting with them recently. I have observed that when I apply them to my model, the performance of the model improves, ...
David Díaz's user avatar
1 vote
1 answer
28 views

How to sample for compliance when a portion of the population is already known to be non-compliant?

Say I wanted a representative sample to estimate the portion of a population that is compliant on "doing their taxes correctly". Normally, I'd do a random sample of that population to make ...
coip's user avatar
  • 315
0 votes
0 answers
299 views

My CNN is not learning but just memorizing [duplicate]

So there has been similar posts but none of them solves my problem, so I decided to created a new question. I'm working on a regression project where I intend to use CNN to predict material properties,...
xshang's user avatar
  • 1
1 vote
0 answers
43 views

Is there a name for this "generalized PCA"?

I was trying to understand the difference between Principal Component Analysis (PCA) and Canonical Covariate Analysis (CCA), and noticed that if you write them down to look as similar as possible, ...
dankness's user avatar
  • 111
2 votes
0 answers
177 views

Overfitting, generalization, data augmentation, regularization, how do they relate to each other? How to measure?

Recent work such as Deep Double Descent shows that overfitting is not really a problem with large models, even without any data augmentation or regularization (L2 weight norm, dropout or so). Edit: Ok,...
Albert's user avatar
  • 1,245
0 votes
0 answers
28 views

Rule of thumb for removing / keeping attribute based on occurrence frequencies among training observations?

I have a training dataset expressed with binary values, where 1 indicates an attribute is used in an observation, and 0 indicates it is not. I was wondering if I should remove an attribute from the ...
GabiX's user avatar
  • 23
5 votes
1 answer
72 views

Is there a multivariate joint Amoroso distribution?

The Amoroso distribution is a remarkable feat of abstraction as it exactly or asymptotically generalizes dozens of named probability distributions. Is there a published/pre-published treatment of ...
Galen's user avatar
  • 8,125
1 vote
0 answers
124 views

External loss functions for Spectral/Density-based clustering

In this article, Abou-Mustafa and Schuurmans proposed a method that makes it easy to decide what unsupervised learning algorithm generalizes 'better' to the entire dataset. In particular, this needs ...
drommedaris's user avatar
4 votes
0 answers
75 views

What are the tradeoffs of using the generalized $f$-median?

The generalized f-mean is a generalization of multiple estimators, and even generalizes the generalized mean. For some invertible function $f$, and $k$-dimensional vector, it is given as: $$M_f(\vec{x}...
Galen's user avatar
  • 8,125
5 votes
1 answer
265 views

Mean of Generalization of the Dirichlet Distribution

I know that if $X_{1},X_{2},...X_{n}$ are independent $\mathrm{Gamma}(\alpha_{i},\theta)$ - distributed variables (notice they all have the same scale parameter $\theta$) and $Y_{i}=\frac{X_{i}}{\sum_{...
bbecon's user avatar
  • 63
2 votes
1 answer
1k views

What does one imply by the term "overgeneralization" in machine learning?

I know overfitting and underfitting in machine learning context, and what generalisation means as well. But, recently I was introduced to an uncommon terminology "overgeneralization" in ...
Umang Agarwal's user avatar
1 vote
0 answers
65 views

Metafor Package: How to conduct Meta Regression with reliability generalization

How to conduct meta regression in "metafor" after I got I2 heterogenity 94%. My study reliability generalization alpha Cronbach, with continuous and categorical moderator variable. Thanks ...
Wahyu Syahputra's user avatar
2 votes
0 answers
28 views

Cannot achieve generalization of machine learning model

I'm working on a balanced, binary classification problem in a time-series (financial) dataset. I am using K-fold cross validation that is adapted for time-series (so that I'm never using future data ...
Vladimir Belik's user avatar
2 votes
2 answers
257 views

SVM Model: What's a healthy number of support vectors?

For a SVM model what is a healthy number of support vectors? or more precisely what's a good ratio of number of support vectors to the total number of training samples, 10%, 20%, 30%, 50% ... 80%? Is ...
SkyWalker's user avatar
  • 925
0 votes
0 answers
47 views

Model selection based on "generalization set"

I'm working on a very general problem in machine learning where I have to choose from different models or from updates which would lead to different models. A first idea was to define a "...
Baschdl's user avatar
  • 143
5 votes
2 answers
854 views

Does up-sampling lead to lots of false positives in production?

Say we have a dataset with a binary outcome variable that takes the positive case (outcome = 1) roughly 20% of the time. Often, we would modify the training set by ...
AmeySMahajan's user avatar
1 vote
1 answer
104 views

Role of misspecification by biased data in the generalization error

I am confused with the role that model misspecification plays in the generalization error, in particular when the misspecification is due to a biased (non representative) training dataset. To clarify ...
synack's user avatar
  • 371
-4 votes
1 answer
59 views

Intuitive explanation on "Generalization " [closed]

I recently worked on Generalization of Gradients. If I'm asked to find Generalization of Gradients or for Dirichlet distribution, etc. I'll do it correctly like a machine. But I didn't understand it. ...
Thalassophile's user avatar
2 votes
1 answer
56 views

Statistics terminology: $n$-way and $m$-sample

In statistics, I see certain things described by "$n$-way" or "$m$-sample." For example, there is "$n$-way" ANOVA for any $n$ and "$m$-sample" t-tests for $m=1,2$. I want to get a handle on what these ...
user avatar