| Not checkable |
Nassim Taleb | Not checkable |
2019 |
almost always have their valuations react in opposite ways when one increases the kurtosis of
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
arguments for the consolidation of beliefs via prices does not lead to prediction markets as discussed in such pieces as [25]
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
One suggestion by the author is for the M5 competition to correct for that by making "predictors" predict the minimum (or maximum) in a…
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
There are five use cases with different hardware requirements
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The best architectures are those that can be saturated with the smallest batch of samples.
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The answer is a resounding yes.
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
it is a central property of fat tails that higher moments are explosive (even "infinite") and count more and more.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
We hold that calibration in frequency (probability) space is an academic exercise (in the bad sense of the word) that mistracks real life…
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
This is rather a problem with the experiment: people do not necessarily separate probabilities from payoffs.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
meaning the fatter the tails, the worse the uncertainty about the expected payoff and the larger the difference between I1 and I2.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
This example is particularly potent as it has no verbalistic correspondence but can be understood by option traders and machine learning.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
unwarranted conclusions that people overestimate tail risk have been chronically made since
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The number of trials required is large because the feedback from the environment is information-poor.
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Succession 2 (fat tails): {0, 0, 0, 0, 0, 0, 5}. Mean variation= 0.71 (same). P/L: g(x) = −18 (bust, really bust, but prediction is…
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Simply, their g(.) function was nonlinear not properly adapted to naive forecasting of the first moment of the random variable.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
the probability distribution of probability (sic) is robust –in other words the distribution of the probability of X doesn’t depend on the…
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
making "calibration" mistakes where it doesn’t matter or can be helpful should be encouraged, not penalized.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
This kind of model can be used to predict multiple scenarios of how surrounding cars are going to move, and to plan a driving policy…
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
for under Gaussian distributions the effect can be marginal, which may have lulled the psychology literature into the conflation.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
It is practically impossible to hedge one with another
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
Video prediction is a subject of wide interest because it may allow future systems, such as robots or self-driving cars, to predict what is…
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
new ideas seem limited by the available hardware (and software)
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Some nonlinear payoff functions, while not lending themselves to verbalistic expressions and "forecasts", can be well captured by ML or…
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The word “architecture” in the context of DL designates the graph of functional modules, not the architecture of the underlying hardware.
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
We start with yj = (f − 1Aj), the difference between a continuous Beta distributed random variable and a discrete Bernoulli one, both…
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
reducing these events to verbalistic "collapse", "disaster" is equivalent to a health insurance payout of a lump sum if one is "very ill"
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
system-level performance is considerably more important than raw speed
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
If a mistake doesn’t cost you anything –or helps you survive or improve your outcomes– it is clearly not a mistake.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Owing to Jensen’s inequality, the discrepancy (I1 − I2) increases under parameter uncertainty, expressed in higher kurtosis
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Many perceived "biases" are shown to be just mischaracterizations by psychologists.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
prices are not binary bets.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
Good results are essential but not sufficient.
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Binary forecasts are not particularly prone to model error; real world payoffs are.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
which works well in situations where one has to forecast the first moment of the distribution and the dispersion around it.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
There can be considerable mathematical and statistical differences between the following two items:
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
P/L tautologically corresponds to the real world distribution, with an absorbing barrier at the survival condition.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The main difficulty is that predicting the future of a video is not achievable exactly because the world is not entirely predictable.
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
What has accounted for the success of GPGPU for DL is their wide availability, generality, programmability, and well-supported software…
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
This insures the predictor meets the constraint of staying above water.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
We have shown that, in risk management (and while forecasting socio-economic and financial variables), one should never operate in…
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
most businesses have severely skewed payoffs, so being calibrated in probability is meaningless.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
One hypothesis is that this missing ingredient is self-supervised learning.
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
But there is no algorithmic reason to batch multiple samples.
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
given that our exposures in the real world rarely map to I1.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Accordingly, Fig. I-5 makes little sense empirically.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
non-programmability was a major limitation
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The use of predictive models that not only predict the evolution of the environment, but also predict the consequences of actions, is key…
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
These appear to be at best one order of magnitude fewer in decisions entailing formal predictions.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
Learning Applied to Document Recognition
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
At the core, calibration metrics such as the Brier score are always thin-tailed, when the variable under measurement is fat-tailed, which…
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
As we can show here, prediction markets may be useful for gamblers, but they cannot hedge economic exposures.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The key advantage of DL is that it alleviates the need to hand-design a feature extractor, as would be required with traditional machine…
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Risk management is about changing the payoff function g(.) rather than making "good forecasts".
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
If the energyminimizing inference procedure is gradient-based, inference hardware will need to support back-propagation.
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Further, we can extract its probability density function of the Brier score for N = 1
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Binary forecasts and calibration metrics via the Brier score belong to the thin-tailed class.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The tools at our disposal fashion our thoughts more than we care to admit.
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Clearly we are dealing with 1) f beta distributed
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
probabilistic calibration requires estimations of the zeroth moment while the real world requires all moments
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
We can proceed to prove directly from there the convergence in distribution for the average
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
Not all layers are represented [37].
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The ideal architecture is a specialized DL-inference accelerator sitting in a standard data-center
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The idea of self-supervised learning is to train a machine to predict any subset of its input from other subsets
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Inconsistent opinions therefore would lead to a violation of arbitrage rules
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
It is very unclear whether analog implementations provide any power dissipation advantages over digital
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
can be close to I2 only under thin-tailed distributions, not under the fat tailed ones.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
This in a nutshell shows how, in the world of finance, "bad" forecasters can make great traders and decision makers, and vice versa.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The scores are normalized to sum to one.
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
The substitution comes from conflating I1 and I2, which becomes an identity if and only if g(.) is constant above
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
A series of binary forecasts will converge very rapidly to a thin-tailed Gaussian even if the underlying distribution is fat-tailed
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Clearly one may be mismeasuring performance if the random variable is in the wrong probability class.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Given that company sales are typically fat tailed, a very low probability of success might still be satisfactory to make a decision.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The history of neural networks is inextricably linked with hardware.
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
While the trader story is mathematically trivial (though the mistake is committed a bit too often)
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
The following simplified example can show us their error and the mismatch between correct forecasting and performance as well as what…
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
Accordingly, miscalibration may be a good idea if it reduces the odds of being absorbed.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
An example of Convolutional Network architecture for
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Yann LeCun | Not checkable |
2019 |
The phrase “differentiable programming” designates the process of writing a program with calls to parameterized functions that…
Yann LeCun · Not checkable · 2019 |
|
| Not checkable |
Nassim Taleb | Not checkable |
2019 |
This quantity can be quite different from the actual loss expectation in case of default.
Nassim Taleb · Not checkable · 2019 |
|
| Not checkable |
Elon Musk | Not checkable |
9 Dec 2018 |
"I thought most likely we would fail," he said.
Elon Musk · Not checkable · 9 Dec 2018 |
|
| Not checkable |
Elon Musk | Not checkable |
9 Dec 2018 |
Musk told Pelley that, when it comes to man's reach for space, "we're at the dawn of a new era."
Elon Musk · Not checkable · 9 Dec 2018 |
|
| Not checkable |
Elon Musk | Not checkable |
9 Dec 2018 |
"had to be ugly and slow and boring like a golf cart."
Elon Musk · Not checkable · 9 Dec 2018 |
|
| Not checkable |
Elon Musk | Not checkable |
9 Dec 2018 |
"I think it's because we're doing these things that seem unlikely to succeed," Musk said. "And we've been fortunate, and at least thus far…
Elon Musk · Not checkable · 9 Dec 2018 |
|
| Not checkable |
Elon Musk | Not checkable |
9 Dec 2018 |
"It's like a little kid fighting a bunch of sumo wrestlers," Musk said. "Usually, the sumo wrestlers win. You know, we're a little scrappy…
Elon Musk · Not checkable · 9 Dec 2018 |
|
| Not checkable |
Elon Musk | Not checkable |
9 Dec 2018 |
"Now I think we'll most likely succeed," Musk answered.
Elon Musk · Not checkable · 9 Dec 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
nothing like it looked to us back in 2007
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
Well I believe the same things happen over and over again and it’s like a disease, if you don’t watch all the cases, you won’t understand…
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
The way it works is the banks are regulated and they are controlled and they are safe and they are overseen, but there are innovations that…
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
I was I was surprised at how curious and interactive people were.
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
Liquidity is the money that comes in, you can have no bank capital and plenty of liquidity and be fine.
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
if it’s a bank, it’s leveraged 10 to 1 and the average assets go down 10%, you’re out of money.
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
That is the pushing on a string phase.
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
if we can just understand and agree on the mechanics of these things, we make a giant leap forward.
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
because a debt is a promise to deliver cash.
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
capitalism right now is not working for the majority of Americans
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
Anyway I don’t think we’ve materially changed those things.
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
We’ve learned some things but not enough things
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
populism is when a strong individual is brought in by a segment — a disenfranchised segment of the population, partially because of…
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
I think every crisis is a bit different and you can’t write the rules so precisely that you can deal with it.
Ray Dalio · Not checkable · 11 Nov 2018 |
|
| Not checkable |
Ray Dalio | Not checkable |
11 Nov 2018 |
History has shown that they are pretty much always allowing the rate of growth to be faster than the rate of capacity to produce
Ray Dalio · Not checkable · 11 Nov 2018 |
|