Ggthjy

When communicating altitude with a '9' in it, should it be pronounced "nine hundred" or "niner hundred"?

Simulating Exploding Dice

How many things? AとBがふたつ

Mortgage adviser recommends a longer term than necessary combined with overpayments

Blender game recording at the wrong time

Can a zero nonce be safely used with AES-GCM if the key is random and never used again?

3 doors, three guards, one stone

Did the new image of black hole confirm the general theory of relativity?

Choo-choo! Word trains

How does modal jazz use chord progressions?

What computer would be fastest for Mathematica Home Edition?

How can I make names more distinctive without making them longer?

Are my PIs rude or am I just being too sensitive?

Classification of bundles, Postnikov towers, obstruction theory, local coefficients

Autumning in love

How to say 'striped' in Latin

What was the last x86 CPU that did not have the x87 floating-point unit built in?

How to politely respond to generic emails requesting a PhD/job in my lab? Without wasting too much time

What is the largest species of polychaete?

The following signatures were invalid: EXPKEYSIG 1397BC53640DB551

Was credit for the black hole image misattributed?

Cold is to Refrigerator as warm is to?

Stopping real property loss from eroding embankment

Active filter with series inductor and resistor - do these exist?

What loss function to use when labels are probabilities?

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty{ margin-bottom:0;
}

2

$begingroup$

What loss function is most appropriate when training a model with target values that are probabilities? For example, I have a 3-output model with x=[some features] and y=[0.2, 0.3, 0.5].

It seems like something like cross-entropy doesn't make sense here since it assumes that a single target is the correct label.

Would something like MSE (after applying softmax) make sense, or is there a better loss function?

neural-networks loss-functions probability-distribution

share|improve this question

asked 6 hours ago

Thomas JohnsonThomas Johnson

1133

New contributor

Thomas Johnson is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

2

$begingroup$

What loss function is most appropriate when training a model with target values that are probabilities? For example, I have a 3-output model with x=[some features] and y=[0.2, 0.3, 0.5].

It seems like something like cross-entropy doesn't make sense here since it assumes that a single target is the correct label.

Would something like MSE (after applying softmax) make sense, or is there a better loss function?

neural-networks loss-functions probability-distribution

share|improve this question

asked 6 hours ago

Thomas JohnsonThomas Johnson

1133

New contributor

Thomas Johnson is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

$begingroup$

What loss function is most appropriate when training a model with target values that are probabilities? For example, I have a 3-output model with x=[some features] and y=[0.2, 0.3, 0.5].

It seems like something like cross-entropy doesn't make sense here since it assumes that a single target is the correct label.

Would something like MSE (after applying softmax) make sense, or is there a better loss function?

neural-networks loss-functions probability-distribution

share|improve this question

asked 6 hours ago

Thomas JohnsonThomas Johnson

1133

New contributor

Thomas Johnson is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

share|improve this question

asked 6 hours ago

Thomas JohnsonThomas Johnson

1133

New contributor

Thomas Johnson is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

share|improve this question

asked 6 hours ago

Thomas JohnsonThomas Johnson

1133

New contributor

Thomas Johnson is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 6 hours ago

Thomas JohnsonThomas Johnson

1133

New contributor

Thomas Johnson is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 6 hours ago

Thomas JohnsonThomas Johnson

1133

1 Answer
1

active

oldest

votes

3

$begingroup$

Actually, the cross-entropy loss function would be appropriate here, since it measures the "distance" between a distribution $q$ and the "true" distribution $p$.

You are right, though, that using a loss function called "cross_entropy" in many APIs would be a mistake. This is because these functions, as you said, assume a one-hot label. You would need to use the general cross-entropy function,

$$H(p,q)=-sum_{xin X} p(x) log q(x).$$
$ $

Note that one-hot labels would mean that
$$
p(x) =
begin{cases}
1 & text{if }x text{ is the true label}\
0 & text{otherwise}
end{cases}$$

which causes the cross-entropy $H(p,q)$ to reduce to the form you're familiar with:

$$H(p,q) = -log q(x_{label})$$

share|improve this answer

answered 6 hours ago

Philip RaeisghasemPhilip Raeisghasem

988119

$endgroup$

add a comment | 

Your Answer

StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "658"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});

function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
noCode: true, onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});


}
});

Thomas Johnson is a new contributor. Be nice, and check out our Code of Conduct.

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Sign up using Google

Sign up using Facebook

Sign up using Email and Password

Post as a guest

Name

Email

Required, but never shown

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fai.stackexchange.com%2fquestions%2f11816%2fwhat-loss-function-to-use-when-labels-are-probabilities%23new-answer', 'question_page');
}
);

Post as a guest

Name

Email

Required, but never shown

3

$begingroup$

Actually, the cross-entropy loss function would be appropriate here, since it measures the "distance" between a distribution $q$ and the "true" distribution $p$.

You are right, though, that using a loss function called "cross_entropy" in many APIs would be a mistake. This is because these functions, as you said, assume a one-hot label. You would need to use the general cross-entropy function,

$$H(p,q)=-sum_{xin X} p(x) log q(x).$$
$ $

Note that one-hot labels would mean that
$$
p(x) =
begin{cases}
1 & text{if }x text{ is the true label}\
0 & text{otherwise}
end{cases}$$

which causes the cross-entropy $H(p,q)$ to reduce to the form you're familiar with:

$$H(p,q) = -log q(x_{label})$$

share|improve this answer

answered 6 hours ago

Philip RaeisghasemPhilip Raeisghasem

988119

$endgroup$

add a comment | 

3

$begingroup$

Actually, the cross-entropy loss function would be appropriate here, since it measures the "distance" between a distribution $q$ and the "true" distribution $p$.

You are right, though, that using a loss function called "cross_entropy" in many APIs would be a mistake. This is because these functions, as you said, assume a one-hot label. You would need to use the general cross-entropy function,

$$H(p,q)=-sum_{xin X} p(x) log q(x).$$
$ $

Note that one-hot labels would mean that
$$
p(x) =
begin{cases}
1 & text{if }x text{ is the true label}\
0 & text{otherwise}
end{cases}$$

which causes the cross-entropy $H(p,q)$ to reduce to the form you're familiar with:

$$H(p,q) = -log q(x_{label})$$

share|improve this answer

answered 6 hours ago

Philip RaeisghasemPhilip Raeisghasem

988119

$endgroup$

add a comment | 

$begingroup$

Actually, the cross-entropy loss function would be appropriate here, since it measures the "distance" between a distribution $q$ and the "true" distribution $p$.

You are right, though, that using a loss function called "cross_entropy" in many APIs would be a mistake. This is because these functions, as you said, assume a one-hot label. You would need to use the general cross-entropy function,

$$H(p,q)=-sum_{xin X} p(x) log q(x).$$
$ $

Note that one-hot labels would mean that
$$
p(x) =
begin{cases}
1 & text{if }x text{ is the true label}\
0 & text{otherwise}
end{cases}$$

which causes the cross-entropy $H(p,q)$ to reduce to the form you're familiar with:

$$H(p,q) = -log q(x_{label})$$

share|improve this answer

answered 6 hours ago

Philip RaeisghasemPhilip Raeisghasem

988119

$endgroup$

share|improve this answer

answered 6 hours ago

Philip RaeisghasemPhilip Raeisghasem

988119

answered 6 hours ago

Philip RaeisghasemPhilip Raeisghasem

988119

answered 6 hours ago

Philip RaeisghasemPhilip Raeisghasem

988119