activity
20122023
most citedDerivations and Alberti representations

42 citations · 69 across the 13 of their papers we have counts for

collaborators

19 papers

cs.LG2023★ 4 cited

Theoretical and Practical Perspectives on what Influence Functions Do

Andrea Schioppa, Katja Filippova, Ivan Titov +1

Influence functions (IF) have been seen as a technique for explaining model predictions through the lens of the training data. Their utility is assumed to be in identifying trainin…

cs.CL2023★ 5 cited

Cross-Lingual Supervision improves Large Language Models Pre-training

Andrea Schioppa, Xavier Garcia, Orhan Firat

The recent rapid progress in pre-training Large Language Models has relied on using self-supervised language modeling objectives like next token prediction or span corruption. On t…

cs.LG2021

Scaling Up Influence Functions

Andrea Schioppa, Polina Zablotskaia, David Vilar +1

We address efficient calculation of influence functions for tracking predictions back to the training data. We propose and analyze a new approach to speeding up the inverse Hessian…

cs.LG2019

Distributed Function Minimization in Apache Spark

Andrea Schioppa

We report on an open-source implementation for distributed function minimization on top of Apache Spark by using gradient and quasi-Newton methods. We show-case it with an applicat…

cs.LG2019

Learning to Transport with Neural Networks

Andrea Schioppa

We compare several approaches to learn an Optimal Map, represented as a neural network, between probability distributions. The approaches fall into two categories: ``Heuristics'' a…

cs.LG2018

Optimality of the final model found via Stochastic Gradient Descent

Andrea Schioppa

We study convergence properties of Stochastic Gradient Descent (SGD) for convex objectives without assumptions on smoothness or strict convexity. We consider the question of establ…

math.MG2017

An example of a doubling "inherently" infinite-dimensional subset of

Andrea Schioppa

We construct a doubling subset of which cannot be biLipschitz embedded in any finite dimensional Euclidean space. This answers a question of Lang and Plaut.

math.CA2016

Lipschitz functions with prescribed blowups at many points

Andrea Marchese, Andrea Schioppa

In this paper we prove generalizations of Lusin-type theorems for gradients due to Giovanni Alberti, where we replace the Lebesgue measure with any Radon measure . We apply this…

math.MG2016★ 4 cited

An example of a differentiability space which is PI-unrectifiable

Andrea Schioppa

We construct a (Lipschitz) differentiability space which has at generic points a disconnected tangent and thus does not contain positive measure subsets isometric to positive measu…

math.MG2016

Unrectifiable normal currents in Euclidean spaces

Andrea Schioppa

We construct in a -dimensional simple normal current whose support is purely -unrectifiable. The result is sharp because the support of a normal current ca…

math.MG2015

Examples of -unrectifiable normal currents

Andrea Schioppa

We construct new examples of normal (metric) currents using inverse systems of cube complexes. For any we provide examples of -dimensional normal currents whose associa…

math.MG2015★ 11 cited

The Lip-lip equality is stable under blow-up

Andrea Schioppa

We show that at generic points blow-ups/tangents of differentiability spaces are still differentiability spaces; this implies that an analytic condition introduced by Keith as an i…

math.MG2015

PI spaces with analytic dimension 1 and arbitrary topological dimension

Bruce Kleiner, Andrea Schioppa

For every n, we construct a metric measure space that is doubling, satisfies a Poincare inequality in the sense of Heinonen-Koskela, has topological dimension n, and has a measurab…

math.MG2015

The Poincaré Inequality does not improve with blow-up

Andrea Schioppa

For each we construct a family of metric measure spaces which is closed under the operation of taking weak-tangents (i.e.~blow-ups), and such that each element of …

math.MG2015

Infinitesimal structure of differentiability spaces, and metric differentiation

Jeff Cheeger, Bruce Kleiner, Andrea Schioppa

We prove metric differentiation for differentiability spaces in the sense of Cheeger. As corollaries we give a new proof that the minimal generalized upper gradient coincides with…

math.MG2014

Poincaré inequalities for mutually singular measures

Andrea Schioppa

Using an inverse system of metric graphs as in: J. Cheeger and B. Kleiner, "Inverse limit spaces satisfying a Poincaré inequality", we provide a simple example of a metric space $X…

math.MG2014

Metric Currents and Alberti representations

Andrea Schioppa

We relate Ambrosio-Kirchheim metric currents to Alberti representations and Weaver derivations. In particular, given a metric current , we show that if the module $\mathscr{X}(\…

math.MG2013★ 42 cited

Derivations and Alberti representations

Andrea Schioppa

We relate generalized Lebesgue decompositions of measures in terms of curve fragments (Alberti representations) and Weaver derivations. This correspondence leads to a geometric cha…

math.MG2012★ 3 cited

On the relationship between derivations and measurable differentiable structures on metric measure spaces

Andrea Schioppa

We investigate the relationship between measurable differentiable structures on doubling metric measure spaces and derivations. We prove: [1] a decomposition theorem for the module…