Sfrgttk

If A makes B more likely then B makes A more likely"

Complexity of many constant time steps with occasional logarithmic steps

What is the order of Mitzvot in Rambam's Sefer Hamitzvot?

Why use gamma over alpha radiation?

Cauchy Sequence Characterized only By Directly Neighbouring Sequence Members

Why does this iterative way of solving of equation work?

Was credit for the black hole image misattributed?

Area of a 2D convex hull

Simulating Exploding Dice

Need a suitable toxic chemical for a murder plot in my novel

How does modal jazz use chord progressions?

Blender game recording at the wrong time

How to market an anarchic city as a tourism spot to people living in civilized areas?

What's the point in a preamp?

Stopping real property loss from eroding embankment

Using "nakedly" instead of "with nothing on"

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

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

Replacing HDD with SSD; what about non-APFS/APFS?

What do I do if technical issues prevent me from filing my return on time?

No baking right

What would be Julian Assange's expected punishment, on the current English criminal law?

Why is there no army of Iron-Mans in the MCU?

What are the performance impacts of 'functional' Rust?

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