all AI news
Benefits of Additive Noise in Composing Classes with Bounded Capacity. (arXiv:2206.07199v1 [stat.ML])
June 16, 2022, 1:12 a.m. | Alireza Fathollah Pour, Hassan Ashtiani
stat.ML updates on arXiv.org arxiv.org
We observe that given two (compatible) classes of functions $\mathcal{F}$ and
$\mathcal{H}$ with small capacity as measured by their uniform covering
numbers, the capacity of the composition class $\mathcal{H} \circ \mathcal{F}$
can become prohibitively large or even unbounded. We then show that adding a
small amount of Gaussian noise to the output of $\mathcal{F}$ before composing
it with $\mathcal{H}$ can effectively control the capacity of $\mathcal{H}
\circ \mathcal{F}$, offering a general recipe for modular design. To prove our
results, we …
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Senior ML Researcher - 3D Geometry Processing | 3D Shape Generation | 3D Mesh Data
@ Promaton | Europe
Analytics Engineer
@ CircleCI | Remote (US), Remote (Canada), San Francisco, Denver
Bilingual Executive Assistant/Data Analyst - (French and English) - Export
@ Dangote Group | Lagos, Lagos, Nigeria
Workday Services Data Lead
@ WPP | Mexico City, Mexico
Business Data Analyst
@ Nordea | Tallinn, EE, 11415
Data Integrity Lead
@ BioNTech SE | Gaithersburg, MD, US, MD 20878