Research
On-device research index

arXiv research

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.

168,742 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Sep 202119922001200920172026
2 results for “non-spuriousness”
Desiderata for Representation Learning: A Causal Perspectivestat.ML

The paper formalizes criteria for non-spurious and disentangled representations using causal methods.

problem Formalizing criteria for non-spurious and disentangled representations in representation learning.
method Causal perspective, counterfactual quantities, observable consequences of causal assertions.
result Computable metrics for assessing representation learning based on observed data.
representation learningcausalitydisentanglementnon-spuriousnesscounterfactuals
2021-09-08abs ↗pdf ↗
Towards Trustworthy Explanation: On Causal Rationalizationcs.LG

A new approach to rationalization identifies true rationales by considering causal relationships.

problem Existing rationalization methods struggle with spuriousness, where snippets with similar contributions are hard to distinguish.
method The method leverages causal inference to identify non-spurious rationales, defining probabilities of causation based on a structural causal model.
result The proposed causal rationalization outperforms existing methods on real-world datasets.
causal inferencerationalizationspuriousnessstructural causal modelnatural language processing
2023-06-25abs ↗pdf ↗