A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
The paper develops algorithms to find a robust summary of data under deletion, achieving good approximation guarantees.
RS-Del provides robustness for sequence classifiers against edit distance attacks.
The paper tackles robust submodular maximization under matroid constraints, providing approximation algorithms for summary extraction.
Many real datasets contain values missing not at random (MNAR). In this scenario, investigators often perform list-wise deletion, or delete samples with any missing values, before applying causal discovery algorithms. List-wise deletion is a sound and general strategy when paired with algorithms such as FCI and RFCI, b…
New approach protects privacy of deleted records in machine learning.
Paper tackles adaptive deletion of data points from trained models.
This research tackles data deletion in linear regression with noisy SGD, finding perfect deleted points.
We propose the Insertion-Deletion Transformer, a novel transformer-based neural architecture and training method for sequence generation. The model consists of two phases that are executed iteratively, 1) an insertion phase and 2) a deletion phase. The insertion phase parameterizes a distribution of insertions on the c…
Efficient algorithms for deleting data from machine learning models without significantly affecting performance.
Paper proposes a fast method for approximate data deletion in generative models.
New method for efficiently deleting data from ML models.
We study the problem of maximizing a monotone set function subject to a cardinality constraint in the setting where some number of elements is deleted from the returned set. The focus of this work is on the worst-case adversarial setting. While there exist constant-factor guarantees when the function is submodu…
Study on deleting user data in linear regression models to maintain limited memory.
New examples show deletion type admissible pairs can be rigid under rational saturation.
ID-ExpO fine-tunes neural networks for more faithful explanations.
The paper compares two methods for handling missing data in causal discovery.
We observe the effects of the three different events that cause spread changes in the order book, namely trades, deletions and placement of limit orders. By looking at the frequencies of the relative amounts of price changing events, we discover that deletions of orders open the bid-ask spread of a stock more often tha…
We show that deleting an edge of a 3-cycle in an intrinsically knotted graph gives an intrinsically linked graph.
Intense recent discussions have focused on how to provide individuals with control over when their data can and cannot be used --- the EU's Right To Be Forgotten regulation is an example of this effort. In this paper we initiate a framework studying what to do when it is no longer permissible to deploy models derivativ…
A new method combines OCSVM with representation learning for UAD.
DaRE forests enable efficient data deletion from random forests.
This article proposes a generalisation of the delete- jackknife to solve hyperparameter selection problems for time series. I call it artificial delete- jackknife to stress that this approach substitutes the classic removal step with a fictitious deletion, wherein observed datapoints are replaced with artificial …
We use a variation on the commutator collection process to characterize those pure braids which become trivial when any one strand is deleted, or, more generally, those pure braids which become trivial when all the strands in any one of a list of sets of strands is deleted.
Deep neural networks for natural language processing tasks are vulnerable to adversarial input perturbations. In this paper, we present a versatile language for programmatically specifying string transformations -- e.g., insertions, deletions, substitutions, swaps, etc. -- that are relevant to the task at hand. We then…
Graph pruning improves neural network performance by addressing squashing and smoothing issues.
Develops structured noise for more accurate graph classifier robustness certificates.
Gordon and Litherland showed that all compact, unoriented, possibly non-orientable surfaces in bounded by a link are realted by attaching/deleting tubes and half twisted bands. In this note we give an elementary proof for this result.
The configuration space of ordered pairs of distinct points in a manifold , also known as the deleted square of , is not a homotopy invariant of : Longoni and Salvatore produced examples of homotopy equivalent lens spaces and of dimension three for which and are not homoto…
We propose a framework for verifying data deletion in MLaaS systems.
New graph shows edge deletion/contraction doesn't always result in intrinsically linked graphs.
Recently enacted legislation grants individuals certain rights to decide in what fashion their personal data may be used, and in particular a "right to be forgotten". This poses a challenge to machine learning: how to proceed when an individual retracts permission to use data which has been part of the training process…
New algorithms delete user data from machine learning models efficiently.
Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification. However, only few work has addressed the adversarial robustness of GNNs. In this paper, we first present a novel gradient-based attack method that fa…
Second-order optimizers retain residual information after data deletion, affecting machine unlearning.
We investigate the problem of reliable communication between two legitimate parties over deletion channels under an active eavesdropping (aka jamming) adversarial model. To this goal, we develop a theoretical framework based on probabilistic finite-state automata to define novel encoding and decoding schemes that ensur…
Efficiently adds or deletes data in GBDT models.
Applications in machine learning, optimization, and control require the sequential selection of a few system elements, such as sensors, data, or actuators, to optimize the system performance across multiple time steps. However, in failure-prone and adversarial environments, sensors get attacked, data get deleted, and a…
Graphs can be fooled by small edge changes, but this work protects them.
New algorithms reduce matching market regret to log(T) with improved stability.
DeltaGrad rapidly retrain models with minimal data changes.
Perturbation-based explanation methods often measure the contribution of an input feature to an image classifier's outputs by heuristically removing it via e.g. blurring, adding noise, or graying out, which often produce unrealistic, out-of-samples. Instead, we propose to integrate a generative inpainter into three rep…
GNNs robustness in community detection is studied with various perturbations.
We introduce agents that use object-oriented reasoning to consider alternate states of the world in order to more quickly find solutions to problems. Specifically, a hierarchical controller directs a low-level agent to behave as if objects in the scene were added, deleted, or modified. The actions taken by the controll…
New framework for consistent submodular maximization with insertions and deletions.
DVWU framework improves model performance by considering data value heterogeneity.
Bayesian models can be tricked into believing false data.
New algorithm for maximizing submodular functions in real-time data changes.
We propose an approach for approximating the partition function which is based on two steps: (1) computing the partition function of a simplified model which is obtained by deleting model edges, and (2) rectifying the result by applying an edge-by-edge correction. The approach leads to an intuitive framework in which o…