FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3179734518> ?p ?o ?g. }

• W3179734518 abstract "In this work, we show, for the well-studied problem of learning parity under noise, where a learner tries to learn $x=(x_1,ldots,x_n) in {0,1}^n$ from a stream of random linear equations over $mathrm{F}_2$ that are correct with probability $frac{1}{2}+varepsilon$ and flipped with probability $frac{1}{2}-varepsilon$, that any learning algorithm requires either a memory of size $Omega(n^2/varepsilon)$ or an exponential number of samples. In fact, we study memory-sample lower bounds for a large class of learning problems, as characterized by [GRT'18], when the samples are noisy. A matrix $M: A times X rightarrow {-1,1}$ corresponds to the following learning problem with error parameter $varepsilon$: an unknown element $x in X$ is chosen uniformly at random. A learner tries to learn $x$ from a stream of samples, $(a_1, b_1), (a_2, b_2) ldots$, where for every $i$, $a_i in A$ is chosen uniformly at random and $b_i = M(a_i,x)$ with probability $1/2+varepsilon$ and $b_i = -M(a_i,x)$ with probability $1/2-varepsilon$ ($0<varepsilon< frac{1}{2}$). Assume that $k,ell, r$ are such that any submatrix of $M$ of at least $2^{-k} cdot |A|$ rows and at least $2^{-ell} cdot |X|$ columns, has a bias of at most $2^{-r}$. We show that any learning algorithm for the learning problem corresponding to $M$, with error, requires either a memory of size at least $Omegaleft(frac{k cdot ell}{varepsilon} right)$, or at least $2^{Omega(r)}$ samples. In particular, this shows that for a large class of learning problems, same as those in [GRT'18], any learning algorithm requires either a memory of size at least $Omegaleft(frac{(log |X|) cdot (log |A|)}{varepsilon}right)$ or an exponential number of noisy samples. Our proof is based on adapting the arguments in [Raz'17,GRT'18] to the noisy case." @default.
• W3179734518 created "2021-07-19" @default.
• W3179734518 creator A5041545934 @default.
• W3179734518 creator A5051447099 @default.
• W3179734518 creator A5068103506 @default.
• W3179734518 creator A5071663193 @default.
• W3179734518 date "2021-07-05" @default.
• W3179734518 modified "2023-09-23" @default.
• W3179734518 title "Memory-Sample Lower Bounds for Learning Parity with Noise" @default.
• W3179734518 cites W1968540673 @default.
• W3179734518 cites W1995897489 @default.
• W3179734518 cites W2065151783 @default.
• W3179734518 cites W2106458073 @default.
• W3179734518 cites W2171001107 @default.
• W3179734518 cites W2274292897 @default.
• W3179734518 cites W2355911333 @default.
• W3179734518 cites W2465504090 @default.
• W3179734518 cites W2594724913 @default.
• W3179734518 cites W2626222921 @default.
• W3179734518 cites W2742151425 @default.
• W3179734518 cites W2769279287 @default.
• W3179734518 cites W2783378791 @default.
• W3179734518 cites W2807842458 @default.
• W3179734518 cites W2899198057 @default.
• W3179734518 cites W2932479067 @default.
• W3179734518 cites W2945428111 @default.
• W3179734518 cites W2962750290 @default.
• W3179734518 cites W2962929471 @default.
• W3179734518 cites W2963951786 @default.
• W3179734518 cites W2964181194 @default.
• W3179734518 cites W2964923747 @default.
• W3179734518 cites W3035699347 @default.
• W3179734518 cites W3115679599 @default.
• W3179734518 cites W3159171078 @default.
• W3179734518 hasPublicationYear "2021" @default.
• W3179734518 type Work @default.
• W3179734518 sameAs 3179734518 @default.
• W3179734518 citedByCount "0" @default.
• W3179734518 crossrefType "posted-content" @default.
• W3179734518 hasAuthorship W3179734518A5041545934 @default.
• W3179734518 hasAuthorship W3179734518A5051447099 @default.
• W3179734518 hasAuthorship W3179734518A5068103506 @default.
• W3179734518 hasAuthorship W3179734518A5071663193 @default.
• W3179734518 hasConcept C114614502 @default.
• W3179734518 hasConcept C118615104 @default.
• W3179734518 hasConcept C121332964 @default.
• W3179734518 hasConcept C134306372 @default.
• W3179734518 hasConcept C154945302 @default.
• W3179734518 hasConcept C2778445095 @default.
• W3179734518 hasConcept C2779557605 @default.
• W3179734518 hasConcept C33923547 @default.
• W3179734518 hasConcept C41008148 @default.
• W3179734518 hasConcept C62520636 @default.
• W3179734518 hasConcept C77553402 @default.
• W3179734518 hasConceptScore W3179734518C114614502 @default.
• W3179734518 hasConceptScore W3179734518C118615104 @default.
• W3179734518 hasConceptScore W3179734518C121332964 @default.
• W3179734518 hasConceptScore W3179734518C134306372 @default.
• W3179734518 hasConceptScore W3179734518C154945302 @default.
• W3179734518 hasConceptScore W3179734518C2778445095 @default.
• W3179734518 hasConceptScore W3179734518C2779557605 @default.
• W3179734518 hasConceptScore W3179734518C33923547 @default.
• W3179734518 hasConceptScore W3179734518C41008148 @default.
• W3179734518 hasConceptScore W3179734518C62520636 @default.
• W3179734518 hasConceptScore W3179734518C77553402 @default.
• W3179734518 hasOpenAccess W3179734518 @default.
• W3179734518 hasRelatedWork W1741819542 @default.
• W3179734518 hasRelatedWork W2028364639 @default.
• W3179734518 hasRelatedWork W2810395196 @default.
• W3179734518 hasRelatedWork W2914662878 @default.
• W3179734518 hasRelatedWork W2951657806 @default.
• W3179734518 hasRelatedWork W2952088850 @default.
• W3179734518 hasRelatedWork W2953023504 @default.
• W3179734518 hasRelatedWork W2963368094 @default.
• W3179734518 hasRelatedWork W2963445202 @default.
• W3179734518 hasRelatedWork W3041014940 @default.
• W3179734518 hasRelatedWork W3104465848 @default.
• W3179734518 hasRelatedWork W3112047060 @default.
• W3179734518 hasRelatedWork W3177293367 @default.
• W3179734518 hasRelatedWork W3195761312 @default.
• W3179734518 hasRelatedWork W3202425833 @default.
• W3179734518 hasRelatedWork W3205208266 @default.
• W3179734518 hasRelatedWork W3210340672 @default.
• W3179734518 hasRelatedWork W3211350961 @default.
• W3179734518 hasRelatedWork W87237856 @default.
• W3179734518 hasRelatedWork W3103538977 @default.
• W3179734518 isParatext "false" @default.
• W3179734518 isRetracted "false" @default.
• W3179734518 magId "3179734518" @default.
• W3179734518 workType "article" @default.