Trjtdtk

Confused about Cramer-Rao lower bound and CLT

What is the English pronunciation of "pain au chocolat"?

Will number of steps recorded on FitBit/any fitness tracker add up distance in PokemonGo?

Microchip documentation does not label CAN buss pins on micro controller pinout diagram

US tourist/student visa

What fields between the rationals and the reals allow a good notion of 2D distance?

Why is so much work done on numerical verification of the Riemann Hypothesis?

Is a Java collection guaranteed to be in a valid, usable state after a ConcurrentModificationException?

How to make money from a browser who sees 5 seconds into the future of any web page?

C++ copy constructor called at return

Is there a RAID 0 Equivalent for RAM?

Review your own paper in Mathematics

What is Cash Advance APR?

Is it ethical to recieve stipend after publishing enough papers?

Stack Interview Code methods made from class Node and Smart Pointers

When were female captains banned from Starfleet?

Did the UK lift the requirement for registering SIM cards?

How to draw a matrix with arrows in limited space

Does the reader need to like the PoV character?

Is this toilet slogan correct usage of the English language?

How much theory knowledge is actually used while playing?

Can I cause damage to electrical appliances by unplugging them when they are turned on?

Can I say "fingers" when referring to toes?

Why the "ls" command is showing the permissions of files in a FAT32 partition?

Logistic function with a slope but no asymptotes?

Has Arcsinh ever been considered as a neural network activation function?Effect of e when using the Sigmoid Function as an activation functionApproximation of Δoutput in context of Sigmoid functionModification of Sigmoid functionFinding the center of a logistic curveInput and Output range of the composition of Gaussian and Sigmoidal functions and it's entropyFinding the slope at different points in a sigmoid curveQuestion about Sigmoid Function in Logistic RegressionHas Arcsinh ever been considered as a neural network activation function?The link between logistic regression and logistic sigmoidHow can I even out the output of the sigmoid function?

7

$begingroup$

The logistic function has an output range 0 to 1, and asymptotic slope is zero on both sides.

What is an alternative to a logistic function that doesn't flatten out completely at its ends? Whose asymptotic slopes are approaching zero but not zero, and the range is infinite?

sigmoid-curve

share|cite|improve this question

edited 16 hours ago

Neil G

9,79012970

asked yesterday

AksakalAksakal

39k452120

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  The title seems to disagree with how i read your question -- is this new function required to have asymptotes or not?
  $endgroup$
  – jld
  yesterday
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Basically I want a function that looks like sigmoid but has a slope
  $endgroup$
  – Aksakal
  yesterday
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  I just updated -- is that more what you mean? I'm still not sure what you mean by a "slope". Do you mean a sigmoid shape but with $lim_xtopminftyf(x) = pm infty$, i.e. it doesn't flatten out into horizontal asymptotes at $|x|$ grows?
  $endgroup$
  – jld
  yesterday
  

  
  
  
  


• 
  
  
  

  
  5
  

  
  
  
  
  
  

  
  $begingroup$
  $operatornamesign(x)log(1 + |x|)$?
  $endgroup$
  – steveo'america
  yesterday
  
  

  
  
  
  


• 
  
  
  

  
  3
  

  
  
  
  
  
  

  
  $begingroup$
  Beginning of the decade called, it wants its neural network activation functions back. (Sorry bad joke, but realistically this is why people moved to ReLUs) (+1 though, relevant question)
  $endgroup$
  – usεr11852
  yesterday
  
  

  
  
  
  

 | 
show 4 more comments

7

$begingroup$

The logistic function has an output range 0 to 1, and asymptotic slope is zero on both sides.

What is an alternative to a logistic function that doesn't flatten out completely at its ends? Whose asymptotic slopes are approaching zero but not zero, and the range is infinite?

sigmoid-curve

share|cite|improve this question

edited 16 hours ago

Neil G

9,79012970

asked yesterday

AksakalAksakal

39k452120

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  The title seems to disagree with how i read your question -- is this new function required to have asymptotes or not?
  $endgroup$
  – jld
  yesterday
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Basically I want a function that looks like sigmoid but has a slope
  $endgroup$
  – Aksakal
  yesterday
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  I just updated -- is that more what you mean? I'm still not sure what you mean by a "slope". Do you mean a sigmoid shape but with $lim_xtopminftyf(x) = pm infty$, i.e. it doesn't flatten out into horizontal asymptotes at $|x|$ grows?
  $endgroup$
  – jld
  yesterday
  

  
  
  
  


• 
  
  
  

  
  5
  

  
  
  
  
  
  

  
  $begingroup$
  $operatornamesign(x)log(1 + |x|)$?
  $endgroup$
  – steveo'america
  yesterday
  
  

  
  
  
  


• 
  
  
  

  
  3
  

  
  
  
  
  
  

  
  $begingroup$
  Beginning of the decade called, it wants its neural network activation functions back. (Sorry bad joke, but realistically this is why people moved to ReLUs) (+1 though, relevant question)
  $endgroup$
  – usεr11852
  yesterday
  
  

  
  
  
  

 | 
show 4 more comments

$begingroup$

The logistic function has an output range 0 to 1, and asymptotic slope is zero on both sides.

What is an alternative to a logistic function that doesn't flatten out completely at its ends? Whose asymptotic slopes are approaching zero but not zero, and the range is infinite?

sigmoid-curve

share|cite|improve this question

edited 16 hours ago

Neil G

9,79012970

asked yesterday

AksakalAksakal

39k452120

$endgroup$

share|cite|improve this question

edited 16 hours ago

Neil G

9,79012970

asked yesterday

AksakalAksakal

39k452120

share|cite|improve this question

edited 16 hours ago

Neil G

9,79012970

asked yesterday

AksakalAksakal

39k452120

edited 16 hours ago

Neil G

9,79012970

edited 16 hours ago

Neil G

9,79012970

asked yesterday

AksakalAksakal

39k452120

asked yesterday

AksakalAksakal

39k452120

3 Answers
3

active

oldest

votes

10

$begingroup$

Initially I was thinking you did want the horizontal asymptotes at $0$ still; I moved my original answer to the end. If you instead want $lim_xtopm infty f(x) = pminfty$ then would something like the inverse hyperbolic sine work?
$$
textasinh(x) = logleft(x + sqrt1 + x^2right)
$$

This is unbounded but grows like $log$ for large $|x|$ and looks like

I like this function a lot as a data transformation when I've got heavy tails but possibly zeros or negative values.

Another nice thing about this function is that $textasinh'(x) = frac1sqrt1+x^2$ so it has a nice simple derivative.

---

Original answer

$newcommandevarepsilon$Let $f : mathbb Rtomathbb R$ be our function and we'll assume
$$
lim_xtopm infty f(x) = 0.
$$

Suppose $f$ is continuous. Fix $e > 0$. From the asymptotes we have
$$
exists x_1 : x < x_1 implies |f(x)| < e
$$
and analogously there's an $x_2$ such that $x > x_2 implies |f(x)| < e$. Therefore outside of $[x_1,x_2]$ $f$ is within $(-e, e)$. And $[x_1,x_2]$ is a compact interval so by continuity $f$ is bounded on it.

This means that any such function can't be continuous. Would something like
$$
f(x) = begincases x^-1 & xneq 0 \ 0 & x = 0endcases
$$ work?

share|cite|improve this answer

edited yesterday

answered yesterday

jldjld

12.3k23353

$endgroup$

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  The "Related" threads include this unanswered question, in case anyone else has asked themselves the natural followup "what happens if you use asinh in a neural network?" stats.stackexchange.com/questions/359245/…
  $endgroup$
  – Sycorax
  yesterday
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @Sycorax thanks, i was wondering about that
  $endgroup$
  – jld
  yesterday
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  My ears did indeed prick up. I have in the past found asinh() useful when you want to 'do log stuff' to both positive and negative numbers. It also gets around the quandry you can get in, where you need to do a log transform on data with zeros and have to judge an appropriate value of $a$ for $log(x + a)$
  $endgroup$
  – Ingolifs
  23 hours ago
  

  
  
  
  

add a comment | 

9

$begingroup$

You could just add a term to a logistic function:

$$
f(x; a, b, c, d, e)=fraca1+bexp(-cx) + dx + e
$$

The asymptotes will have slopes $d$.

Here is an example with $a=10, b = 1, c = 2, d = frac120, e = -5$:

share|cite|improve this answer

answered yesterday

COOLSerdashCOOLSerdash

16.5k75293

$endgroup$

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  I think this answer is the best because if you zoom out far enough it's just a straight line with a little wiggle in the middle. Gives the most intuitive behavior at large x but retains the sigmoid shape.
  $endgroup$
  – user1717828
  21 hours ago
  

  
  
  
  

add a comment | 

5

$begingroup$

I will go ahead and turn the comment into an answer. I suggest
$$
f(x) = operatornamesign(x)logx,
$$
which has slope tending towards zero, but is unbounded.

edit by popular demand, a plot, for $|x|le 30$:

share|cite|improve this answer

edited 1 hour ago

answered yesterday

steveo'americasteveo'america

23319

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  a graph of the function would be useful
  $endgroup$
  – qwr
  15 hours ago
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @qwr and done...
  $endgroup$
  – steveo'america
  1 hour ago
  

  
  
  
  

add a comment | 

Your Answer

StackExchange.ifUsing("editor", function ()
return StackExchange.using("mathjaxEditing", function ()
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix)
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
);
);
, "mathjax-editing");

StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "65"
;
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
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);



);

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%2fstats.stackexchange.com%2fquestions%2f398551%2flogistic-function-with-a-slope-but-no-asymptotes%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

10

$begingroup$

Initially I was thinking you did want the horizontal asymptotes at $0$ still; I moved my original answer to the end. If you instead want $lim_xtopm infty f(x) = pminfty$ then would something like the inverse hyperbolic sine work?
$$
textasinh(x) = logleft(x + sqrt1 + x^2right)
$$

This is unbounded but grows like $log$ for large $|x|$ and looks like

I like this function a lot as a data transformation when I've got heavy tails but possibly zeros or negative values.

Another nice thing about this function is that $textasinh'(x) = frac1sqrt1+x^2$ so it has a nice simple derivative.

---

Original answer

$newcommandevarepsilon$Let $f : mathbb Rtomathbb R$ be our function and we'll assume
$$
lim_xtopm infty f(x) = 0.
$$

Suppose $f$ is continuous. Fix $e > 0$. From the asymptotes we have
$$
exists x_1 : x < x_1 implies |f(x)| < e
$$
and analogously there's an $x_2$ such that $x > x_2 implies |f(x)| < e$. Therefore outside of $[x_1,x_2]$ $f$ is within $(-e, e)$. And $[x_1,x_2]$ is a compact interval so by continuity $f$ is bounded on it.

This means that any such function can't be continuous. Would something like
$$
f(x) = begincases x^-1 & xneq 0 \ 0 & x = 0endcases
$$ work?

share|cite|improve this answer

edited yesterday

answered yesterday

jldjld

12.3k23353

$endgroup$

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  The "Related" threads include this unanswered question, in case anyone else has asked themselves the natural followup "what happens if you use asinh in a neural network?" stats.stackexchange.com/questions/359245/…
  $endgroup$
  – Sycorax
  yesterday
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @Sycorax thanks, i was wondering about that
  $endgroup$
  – jld
  yesterday
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  My ears did indeed prick up. I have in the past found asinh() useful when you want to 'do log stuff' to both positive and negative numbers. It also gets around the quandry you can get in, where you need to do a log transform on data with zeros and have to judge an appropriate value of $a$ for $log(x + a)$
  $endgroup$
  – Ingolifs
  23 hours ago
  

  
  
  
  

add a comment | 

10

$begingroup$

Initially I was thinking you did want the horizontal asymptotes at $0$ still; I moved my original answer to the end. If you instead want $lim_xtopm infty f(x) = pminfty$ then would something like the inverse hyperbolic sine work?
$$
textasinh(x) = logleft(x + sqrt1 + x^2right)
$$

This is unbounded but grows like $log$ for large $|x|$ and looks like

I like this function a lot as a data transformation when I've got heavy tails but possibly zeros or negative values.

Another nice thing about this function is that $textasinh'(x) = frac1sqrt1+x^2$ so it has a nice simple derivative.

---

Original answer

$newcommandevarepsilon$Let $f : mathbb Rtomathbb R$ be our function and we'll assume
$$
lim_xtopm infty f(x) = 0.
$$

Suppose $f$ is continuous. Fix $e > 0$. From the asymptotes we have
$$
exists x_1 : x < x_1 implies |f(x)| < e
$$
and analogously there's an $x_2$ such that $x > x_2 implies |f(x)| < e$. Therefore outside of $[x_1,x_2]$ $f$ is within $(-e, e)$. And $[x_1,x_2]$ is a compact interval so by continuity $f$ is bounded on it.

This means that any such function can't be continuous. Would something like
$$
f(x) = begincases x^-1 & xneq 0 \ 0 & x = 0endcases
$$ work?

share|cite|improve this answer

edited yesterday

answered yesterday

jldjld

12.3k23353

$endgroup$

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  The "Related" threads include this unanswered question, in case anyone else has asked themselves the natural followup "what happens if you use asinh in a neural network?" stats.stackexchange.com/questions/359245/…
  $endgroup$
  – Sycorax
  yesterday
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @Sycorax thanks, i was wondering about that
  $endgroup$
  – jld
  yesterday
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  My ears did indeed prick up. I have in the past found asinh() useful when you want to 'do log stuff' to both positive and negative numbers. It also gets around the quandry you can get in, where you need to do a log transform on data with zeros and have to judge an appropriate value of $a$ for $log(x + a)$
  $endgroup$
  – Ingolifs
  23 hours ago
  

  
  
  
  

add a comment | 

$begingroup$

Initially I was thinking you did want the horizontal asymptotes at $0$ still; I moved my original answer to the end. If you instead want $lim_xtopm infty f(x) = pminfty$ then would something like the inverse hyperbolic sine work?
$$
textasinh(x) = logleft(x + sqrt1 + x^2right)
$$

This is unbounded but grows like $log$ for large $|x|$ and looks like

I like this function a lot as a data transformation when I've got heavy tails but possibly zeros or negative values.

Another nice thing about this function is that $textasinh'(x) = frac1sqrt1+x^2$ so it has a nice simple derivative.

---

Original answer

$newcommandevarepsilon$Let $f : mathbb Rtomathbb R$ be our function and we'll assume
$$
lim_xtopm infty f(x) = 0.
$$

Suppose $f$ is continuous. Fix $e > 0$. From the asymptotes we have
$$
exists x_1 : x < x_1 implies |f(x)| < e
$$
and analogously there's an $x_2$ such that $x > x_2 implies |f(x)| < e$. Therefore outside of $[x_1,x_2]$ $f$ is within $(-e, e)$. And $[x_1,x_2]$ is a compact interval so by continuity $f$ is bounded on it.

This means that any such function can't be continuous. Would something like
$$
f(x) = begincases x^-1 & xneq 0 \ 0 & x = 0endcases
$$ work?

share|cite|improve this answer

edited yesterday

answered yesterday

jldjld

12.3k23353

$endgroup$

share|cite|improve this answer

edited yesterday

answered yesterday

jldjld

12.3k23353

answered yesterday

jldjld

12.3k23353

answered yesterday

jldjld

12.3k23353

9

$begingroup$

You could just add a term to a logistic function:

$$
f(x; a, b, c, d, e)=fraca1+bexp(-cx) + dx + e
$$

The asymptotes will have slopes $d$.

Here is an example with $a=10, b = 1, c = 2, d = frac120, e = -5$:

share|cite|improve this answer

answered yesterday

COOLSerdashCOOLSerdash

16.5k75293

$endgroup$

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  I think this answer is the best because if you zoom out far enough it's just a straight line with a little wiggle in the middle. Gives the most intuitive behavior at large x but retains the sigmoid shape.
  $endgroup$
  – user1717828
  21 hours ago
  

  
  
  
  

add a comment | 

9

$begingroup$

You could just add a term to a logistic function:

$$
f(x; a, b, c, d, e)=fraca1+bexp(-cx) + dx + e
$$

The asymptotes will have slopes $d$.

Here is an example with $a=10, b = 1, c = 2, d = frac120, e = -5$:

share|cite|improve this answer

answered yesterday

COOLSerdashCOOLSerdash

16.5k75293

$endgroup$

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  I think this answer is the best because if you zoom out far enough it's just a straight line with a little wiggle in the middle. Gives the most intuitive behavior at large x but retains the sigmoid shape.
  $endgroup$
  – user1717828
  21 hours ago
  

  
  
  
  

add a comment | 

$begingroup$

You could just add a term to a logistic function:

$$
f(x; a, b, c, d, e)=fraca1+bexp(-cx) + dx + e
$$

The asymptotes will have slopes $d$.

Here is an example with $a=10, b = 1, c = 2, d = frac120, e = -5$:

share|cite|improve this answer

answered yesterday

COOLSerdashCOOLSerdash

16.5k75293

$endgroup$

share|cite|improve this answer

answered yesterday

COOLSerdashCOOLSerdash

16.5k75293

answered yesterday

COOLSerdashCOOLSerdash

16.5k75293

answered yesterday

COOLSerdashCOOLSerdash

16.5k75293

5

$begingroup$

I will go ahead and turn the comment into an answer. I suggest
$$
f(x) = operatornamesign(x)logx,
$$
which has slope tending towards zero, but is unbounded.

edit by popular demand, a plot, for $|x|le 30$:

share|cite|improve this answer

edited 1 hour ago

answered yesterday

steveo'americasteveo'america

23319

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  a graph of the function would be useful
  $endgroup$
  – qwr
  15 hours ago
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @qwr and done...
  $endgroup$
  – steveo'america
  1 hour ago
  

  
  
  
  

add a comment | 

5

$begingroup$

I will go ahead and turn the comment into an answer. I suggest
$$
f(x) = operatornamesign(x)logx,
$$
which has slope tending towards zero, but is unbounded.

edit by popular demand, a plot, for $|x|le 30$:

share|cite|improve this answer

edited 1 hour ago

answered yesterday

steveo'americasteveo'america

23319

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  a graph of the function would be useful
  $endgroup$
  – qwr
  15 hours ago
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @qwr and done...
  $endgroup$
  – steveo'america
  1 hour ago
  

  
  
  
  

add a comment | 

$begingroup$

I will go ahead and turn the comment into an answer. I suggest
$$
f(x) = operatornamesign(x)logx,
$$
which has slope tending towards zero, but is unbounded.

edit by popular demand, a plot, for $|x|le 30$:

share|cite|improve this answer

edited 1 hour ago

answered yesterday

steveo'americasteveo'america

23319

$endgroup$

share|cite|improve this answer

edited 1 hour ago

answered yesterday

steveo'americasteveo'america

23319

answered yesterday

steveo'americasteveo'america

23319

answered yesterday

steveo'americasteveo'america

23319