Zobrazeno 1 - 10
of 167
pro vyhledávání: '"Javanmard, Adel"'
Recently, there have been numerous studies on feature learning with neural networks, specifically on learning single- and multi-index models where the target is a function of a low-dimensional projection of the input. Prior works have shown that in h
Externí odkaz:
http://arxiv.org/abs/2410.16449
We study the dynamic pricing problem faced by a broker that buys and sells a large number of financial securities in the credit market, such as corporate bonds, government bonds, loans, and other credit-related securities. One challenge in pricing th
Externí odkaz:
http://arxiv.org/abs/2410.14839
Autor:
Das, Rudrajit, Dhillon, Inderjit S., Epasto, Alessandro, Javanmard, Adel, Mao, Jieming, Mirrokni, Vahab, Sanghavi, Sujay, Zhong, Peilin
The performance of a model trained with \textit{noisy labels} is often improved by simply \textit{retraining} the model with its own predicted \textit{hard} labels (i.e., $1$/$0$ labels). Yet, a detailed theoretical characterization of this phenomeno
Externí odkaz:
http://arxiv.org/abs/2406.11206
We consider a weakly supervised learning problem called Learning from Label Proportions (LLP), where examples are grouped into ``bags'' and only the average label within each bag is revealed to the learner. We study various learning rules for LLP tha
Externí odkaz:
http://arxiv.org/abs/2406.00487
This work studies algorithms for learning from aggregate responses. We focus on the construction of aggregation sets (called bags in the literature) for event-level loss functions. We prove for linear regression and generalized linear models (GLMs) t
Externí odkaz:
http://arxiv.org/abs/2402.04987
Due to the rise of privacy concerns, in many practical applications the training data is aggregated before being shared with the learner, in order to protect privacy of users' sensitive responses. In an aggregate learning framework, the dataset is gr
Externí odkaz:
http://arxiv.org/abs/2401.11081
Autor:
Javanmard, Adel, Mirrokni, Vahab
While personalized recommendations systems have become increasingly popular, ensuring user data protection remains a top concern in the development of these learning systems. A common approach to enhancing privacy involves training models using anony
Externí odkaz:
http://arxiv.org/abs/2310.04015
Estimating causal effects from randomized experiments is only feasible if participants agree to reveal their potentially sensitive responses. Of the many ways of ensuring privacy, label differential privacy is a widely used measure of an algorithm's
Externí odkaz:
http://arxiv.org/abs/2308.00957
Autor:
Carey, CJ, Dick, Travis, Epasto, Alessandro, Javanmard, Adel, Karlin, Josh, Kumar, Shankar, Medina, Andres Munoz, Mirrokni, Vahab, Nunes, Gabriel Henrique, Vassilvitskii, Sergei, Zhong, Peilin
Compact user representations (such as embeddings) form the backbone of personalization services. In this work, we present a new theoretical framework to measure re-identification risk in such user representations. Our framework, based on hypothesis t
Externí odkaz:
http://arxiv.org/abs/2304.07210
Autor:
Bhuyan, Rashmi Ranjan, Javanmard, Adel, Kim, Sungchul, Mukherjee, Gourab, Rossi, Ryan A., Yu, Tong, Zhao, Handong
We consider dynamic pricing strategies in a streamed longitudinal data set-up where the objective is to maximize, over time, the cumulative profit across a large number of customer segments. We consider a dynamic model with the consumers' preferences
Externí odkaz:
http://arxiv.org/abs/2303.15652