Universal epsilon-approximators for Integrals

By Michael Langberg, Leonard J. Schulman. 2010

65 citations recorded by the source corpus.

Subfields: Applied Mathematics, Artificial Intelligence, Geometry and Topology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Applied Mathematics

1. Francis R. Bach
2. Ben Mussay
3. Margarita Osadchy
4. Vladimir Braverman
5. Samson Zhou
6. Dan Feldman
7. Jing Lei

In Artificial Intelligence

1. Dan Feldman
2. Chris Schwiegelshohn
3. Melanie Schmidt
4. Christian Sohler
5. Francis R. Bach
6. Ben Mussay
7. Margarita Osadchy
8. Vladimir Braverman

In Geometry and Topology

1. Francis R. Bach
2. Ben Mussay
3. Margarita Osadchy
4. Vladimir Braverman
5. Samson Zhou
6. Dan Feldman

Citations in the corpus

• On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions (2015, background): “selected sequentially with the knowledge of the function values at previous points cannot improve the worstcase guarantees. Our results do not recover this lower bound result for adaptivity. Finally, Langberg and Schulman (2010) consider multiplicative errors in computing integrals and mainly focuse”
• Data-Independent Structured Pruning of Neural Networks via Coresets (2020, methodology): “ex hull, and SVM; see details in [43]. Many of the non-deterministic coreset based methods rely on the sensitivity framework, in which elements of the input are sampled according to their sensitivity [29, 5, 48], which is used as a measure of their importance. The sampled elements are usually reweig”
• Core‐sets: An updated survey (2019, methodology): “Then compute a “ uniform ” sample from the weighted set, where each input point is replaced by duplicated points according to its new weight (e.g., Braverman et al., 2016; Langberg & Schulman, 2010).”
• Fair Coresets and Streaming Algorithms for Fair k-Means Clustering (2018, background): “The notion was proposed by Har-Peled and Mazumdar [29] and has since recieved a wide range of attention, see [11, 21, 22, 25, 26, 36] for clustering.”
• Turning big data into tiny data: Constant-size coresets for k-means, PCA and projective clustering (2013, unknown): “e cost of the points. In order to keep the sample unbiased the sample points are weighted with 1=pwhere pis the sampling probability. Instead of sampling from two distributions, Langberg and Schulman [LS10] and Feldman and Langberg [FL11] dene a single distribution, which is a mixture of the two dis”
• BICO: BIRCH Meets Coresets for k-Means Clustering (2013, unknown): “Streaming algorithms using summaries include [8, 10, 11, 12, 20, 21, 22].”
• Data-Independent Neural Pruning via Coresets (2019, methodology): “Many of the non-deterministic coreset based methods rely on the sensitivity framework, in which elements of the input are sampled according to their sensitivity (Langberg & Schulman, 2010; Braverman et al., 2016; Tolochinsky & Feldman, 2018), which is used as a measure of their importance.”