BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2026//speaker//A77EDZ
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-juliacon-2026-ZBQKTY@pretalx.com
DTSTART;TZID=CET:20260813T170000
DTEND;TZID=CET:20260813T171500
DESCRIPTION:Since 2022\, Copulas.jl has provided native support for depende
 nce modeling in Julia. Copulas are multivariate distribution functions on 
 the unit hypercube that allow practitioners to model dependence structures
  separately from marginal behavior. By building on the Distributions.jl fr
 amework\, Copulas.jl integrates seamlessly with Julia’s probabilistic an
 d statistical ecosystem.\n\nIn this talk\, we review the major design impr
 ovements and new features introduced since the first public releases of Co
 pulas.jl. The package now offers a broad collection of classical parametri
 c copula families\, along with tools for evaluating distribution functions
  and densities\, computing dependence measures such as Kendall’s tau and
  Spearman’s rho\, estimating parameters via inversion of moments or maxi
 mum likelihood\, and fitting models to data.\n\nA key feature of the packa
 ge is the Sklar type\, inspired by Sklar’s Theorem\, which enables users
  to construct full multivariate models by combining copulas with arbitrary
  marginal distributions. These composite models are fully compatible with 
 the Distributions.jl API\, making them directly usable in downstream tools
  such as Turing.jl for Bayesian inference.\n\nWe conclude with practical e
 xamples showcasing how the new features of Copulas.jl enable advanced depe
 ndence modeling workflows entirely in native Julia.
DTSTAMP:20260502T093458Z
LOCATION:Room 5
SUMMARY:What's new in Copulas.jl - Oskar Laverny
URL:https://pretalx.com/juliacon-2026/talk/ZBQKTY/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-juliacon-2026-C8UGPM@pretalx.com
DTSTART;TZID=CET:20260814T154500
DTEND;TZID=CET:20260814T160000
DESCRIPTION:Automatic differentiation (AD) is deeply embedded in the Julia 
 ecosystem. Thanks to dual numbers and generic programming\, derivatives of
 ten “just work” across packages. However\, this is not always the case
 . In certain situations (e.g.\, when transcendental functions are evaluate
 d via partial fraction expansions) propagating dual numbers through the im
 plementation may fail\, and for good numerical reasons.\n\nIn this talk\, 
 we present the case of `beta_inc` and `beta_inc_inv` from `SpecialFunction
 s.jl`. Their original implementations relied on partial fraction expansion
 s carefully designed for `Float64` evaluation. While this approach yields 
 numerically stable function values\, it does not automatically provide cor
 rect derivatives under AD. Crucially\, differentiating the partial fractio
 n expansion is not equivalent to computing the partial fraction expansion 
 of the derivative — the latter being significantly more involved.\n\nDra
 wing from the numerical analysis literature (this challenge is not Julia-s
 pecific)\, we implemented exact derivatives for these functions\, as propo
 sed in pull request #506. This work enables the standard automatic differe
 ntiation tools to handle these functions seemlessly. \n\nThese derivatives
  are central to e.g. statistical computing: they are used in the Beta cumu
 lative distribution and quantile functions\, the Student’s t cumulative 
 distribution and quantile functions\, and most importantly for us the mult
 ivariate Student’s t distribution\, which has been asked about several t
 ime on discourse. Prior to this work\, fully differentiable implementation
 s of these models were not available in Distributions.jl.\n\nThis talk goe
 s through the story of `SpecialFunctions.jl`'s pull request #506 titled 
 “Exact chainrules derivatives for beta_inc and beta_inc_inv”\, which s
 olves all these issues and will hopefully be merged by Juliacon.
DTSTAMP:20260502T093458Z
LOCATION:Room 4
SUMMARY:Missing derivative: the example of `beta_inc` and `beta_inc_inv` - 
 Oskar Laverny
URL:https://pretalx.com/juliacon-2026/talk/C8UGPM/
END:VEVENT
END:VCALENDAR