Sven Neth
Biographic Data
| ID | 1116902 |
|---|---|
| NAME | Sven Neth |
| GIVEN NAMES | Sven |
| FAMILY NAME | Neth |
| SIGNATURE | NETH S |
| AFFILIATIONS | University of Pittsburgh |
| ORCID | 0000-0003-4275-7581 |
| VERIFIED | Yes |
| TOTAL WORKS | 8 |
| TOTAL CITATIONS | 3 |
| WORKS AS AUTHOR | 8 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2022 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 1 |
Against Proxy Optimization
I discuss conditions under which maximizing a proxy utility function is harmful and suggest this poses problems for applying decision theory
Variance Normalization and Disagreement
Better Foundations for Subjective Probability
How do we ascribe subjective probability? In decision theory, this question is often addressed by representation theorems, going back to Ramsey (1926), which tell us how to define or measure subjective probability by observable preferences. However, standard representation theorems make strong rationality assumptions, in particular expected utility maximization. How do we ascribe subjective probability to agents which do not satisfy these strong …
Off-switching not guaranteed
Random Emeralds
Suppose we observe many emeralds which are all green. This observation usually provides good evidence that all emeralds are green. However, the emeralds we have observed are also all grue, which means that they are either green and already observed or blue and not yet observed. We usually do not think that our observation provides good evidence that all emeralds are grue. Why? I argue that if we are in the best case for inductive reasoning, we ha…
A Dilemma for Solomonoff Prediction
The framework of Solomonoff prediction assigns prior probability to hypotheses inversely proportional to their Kolmogorov complexity. There are two well-known problems. First, the Solomonoff prior is relative to a choice of universal Turing machine. Second, the Solomonoff prior is not computable. However, there are responses to both problems. Different Solomonoff priors converge with more and more data. Further, there are computable approximation…
Rational Aversion to Information
Is more information always better? Or are there some situations in which more information can make us worse off? Good (1966) argues that expected utility maximizers should always accept more information if the information is cost-free and relevant. But Good's argument presupposes that you are certain you will update by conditionalization. If we relax this assumption and allow agents to be uncertain about updating, these agents can be rationally r…
Accuracy and infinity
We argue that subjective Bayesians face a dilemma: they must offend against the spirit of their permissivism about rational credence or reject the principle that one should avoid accuracy dominance
A Dilemma for Solomonoff Prediction
The framework of Solomonoff prediction assigns prior probability to hypotheses inversely proportional to their Kolmogorov complexity. There are two well-known problems. First, the Solomonoff prior is relative to a choice of universal Turing machine. Second, the Solomonoff prior is not computable. However, there are responses to both problems. Different Solomonoff priors converge with more and more data. Further, there are computable approximation…
Rational Aversion to Information
Is more information always better? Or are there some situations in which more information can make us worse off? Good (1966) argues that expected utility maximizers should always accept more information if the information is cost-free and relevant. But Good's argument presupposes that you are certain you will update by conditionalization. If we relax this assumption and allow agents to be uncertain about updating, these agents can be rationally r…
Accuracy and infinity
We argue that subjective Bayesians face a dilemma: they must offend against the spirit of their permissivism about rational credence or reject the principle that one should avoid accuracy dominance
Accuracy and infinity
We argue that subjective Bayesians face a dilemma: they must offend against the spirit of their permissivism about rational credence or reject the principle that one should avoid accuracy dominance
A Dilemma for Solomonoff Prediction
The framework of Solomonoff prediction assigns prior probability to hypotheses inversely proportional to their Kolmogorov complexity. There are two well-known problems. First, the Solomonoff prior is relative to a choice of universal Turing machine. Second, the Solomonoff prior is not computable. However, there are responses to both problems. Different Solomonoff priors converge with more and more data. Further, there are computable approximation…
Rational Aversion to Information
Is more information always better? Or are there some situations in which more information can make us worse off? Good (1966) argues that expected utility maximizers should always accept more information if the information is cost-free and relevant. But Good's argument presupposes that you are certain you will update by conditionalization. If we relax this assumption and allow agents to be uncertain about updating, these agents can be rationally r…
Better Foundations for Subjective Probability
How do we ascribe subjective probability? In decision theory, this question is often addressed by representation theorems, going back to Ramsey (1926), which tell us how to define or measure subjective probability by observable preferences. However, standard representation theorems make strong rationality assumptions, in particular expected utility maximization. How do we ascribe subjective probability to agents which do not satisfy these strong …
Off-switching not guaranteed
Random Emeralds
Suppose we observe many emeralds which are all green. This observation usually provides good evidence that all emeralds are green. However, the emeralds we have observed are also all grue, which means that they are either green and already observed or blue and not yet observed. We usually do not think that our observation provides good evidence that all emeralds are grue. Why? I argue that if we are in the best case for inductive reasoning, we ha…
Against Proxy Optimization
I discuss conditions under which maximizing a proxy utility function is harmful and suggest this poses problems for applying decision theory
Variance Normalization and Disagreement
Philosophy (4 works) · Epistemology (3 works) · Bayesian Modeling and Causal Inference (2 works) · Computability, Logic, AI Algorithms (2 works) · Computer Science (2 works) · Decision-Making and Behavioral Economics (2 works) · Economic and Environmental Valuation (2 works) · Epistemology, Ethics, and Metaphysics (2 works) · Metaphysics (2 works) · Philosophy and History of Science (2 works)