arXiv subjects

Mina Karzand

Publications and source records attributed to Mina Karzand.

8 recordsLinked to original sources

arXiv2025

Optimal Sequential Recommendations: Exploiting User and Item Structure

We consider an online model for recommendation systems, with each user being recommended an item at each time-step and providing 'like' or 'dislike' feedback. A latent variable model specifies the user preferences: both users and items are clustered into types. The model captures structure in both the item and user spaces, as used by item-item and user-user collaborative filtering algorithms. We study the situation in which the type preference matrix has i.i.d. entries. Our main contribution is an algorithm that simultaneously uses both item and user structures, proved to be near-optimal via corresponding information-theoretic lower bounds. In particular, our analysis highlights the sub-optimality of using only one of item or user structure (as is done in most collaborative filtering algorithms).

stat.ML↗

arXiv2024

Score Design for Multi-Criteria Incentivization

We present a framework for designing scores to summarize performance metrics. Our design has two multi-criteria objectives: (1) improving on scores should improve all performance metrics, and (2) achieving pareto-optimal scores should achieve pareto-optimal metrics. We formulate our design to minimize the dimensionality of scores while satisfying the objectives. We give algorithms to design scores, which are provably minimal under mild assumptions on the structure of performance metrics. This framework draws motivation from real-world practices in hospital rating systems, where misaligned scores and performance metrics lead to unintended consequences.

cs.CY↗

arXiv2020

MaxiMin Active Learning in Overparameterized Model Classes}

Generating labeled training datasets has become a major bottleneck in Machine Learning (ML) pipelines. Active ML aims to address this issue by designing learning algorithms that automatically and adaptively select the most informative examples for labeling so that human time is not wasted labeling irrelevant, redundant, or trivial examples. This paper proposes a new approach to active ML with nonparametric or overparameterized models such as kernel methods and neural networks. In the context of binary classification, the new approach is shown to possess a variety of desirable properties that allow active learning algorithms to automatically and efficiently identify decision boundaries and data clusters.

cs.LG↗

arXiv2019

Regret Bounds and Regimes of Optimality for User-User and Item-Item Collaborative Filtering

We consider an online model for recommendation systems, with each user being recommended an item at each time-step and providing 'like' or 'dislike' feedback. Each user may be recommended a given item at most once. A latent variable model specifies the user preferences: both users and items are clustered into types. All users of a given type have identical preferences for the items, and similarly, items of a given type are either all liked or all disliked by a given user. We assume that the matrix encoding the preferences of each user type for each item type is randomly generated; in this way, the model captures structure in both the item and user spaces, the amount of structure depending on the number of each of the types. The measure of performance of the recommendation system is the expected number of disliked recommendations per user, defined as expected regret. We propose two algorithms inspired by user-user and item-item collaborative filtering (CF), modified to explicitly make exploratory recommendations, and prove performance guarantees in terms of their expected regret. For two regimes of model parameters, with structure only in item space or only in user space, we prove information-theoretic lower bounds on regret that match our upper bounds up to logarithmic factors. Our analysis elucidates system operating regimes in which existing CF algorithms are nearly optimal.

stat.ML↗

arXiv2018

Learning a Tree-Structured Ising Model in Order to Make Predictions

We study the problem of learning a tree Ising model from samples such that subsequent predictions made using the model are accurate. The prediction task considered in this paper is that of predicting the values of a subset of variables given values of some other subset of variables. Virtually all previous work on graphical model learning has focused on recovering the true underlying graph. We define a distance ("small set TV" or ssTV) between distributions $P$ and $Q$ by taking the maximum, over all subsets $\mathcal{S}$ of a given size, of the total variation between the marginals of $P$ and $Q$ on $\mathcal{S}$; this distance captures the accuracy of the prediction task of interest. We derive non-asymptotic bounds on the number of samples needed to get a distribution (from the same class) with small ssTV relative to the one generating the samples. One of the main messages of this paper is that far fewer samples are needed than for recovering the underlying tree, which means that accurate predictions are possible using the wrong tree.

math.ST↗

arXiv2015

Communication Strategies for Low-Latency Trading

The possibility of latency arbitrage in financial markets has led to the deployment of high-speed communication links between distant financial centers. These links are noisy and so there is a need for coding. In this paper, we develop a gametheoretic model of trading behavior where two traders compete to capture latency arbitrage opportunities using binary signalling. Different coding schemes are strategies that trade off between reliability and latency. When one trader has a better channel, the second trader should not compete. With statistically identical channels, we find there are two different regimes of channel noise for which: there is a unique Nash equilibrium yielding ties; and there are two Nash equilibria with different winners.

cs.IT↗

arXiv2014

Achievable Degrees of Freedom in MIMO Correlatively Changing Fading Channels

The relationship between the transmitted signal and the noiseless received signals in correlatively changing fading channels is modeled as a nonlinear mapping over manifolds of different dimensions. Dimension counting argument claims that the dimensionality of the neighborhood in which this mapping is bijective with probability one is achievable as the degrees of freedom of the system.We call the degrees of freedom achieved by the nonlinear decoding methods the nonlinear degrees of freedom.

cs.IT↗

arXiv2014

Achievability of Nonlinear Degrees of Freedom in Correlatively Changing Fading Channels

A new approach toward the noncoherent communications over the time varying fading channels is presented. In this approach, the relationship between the input signal space and the output signal space of a correlatively changing fading channel is shown to be a nonlinear mapping between manifolds of different dimensions. Studying this mapping, it is shown that using nonlinear decoding algorithms for single input-multiple output (SIMO) and multiple input multiple output (MIMO) systems, extra numbers of degrees of freedom (DOF) are available. We call them the nonlinear degrees of freedom.

cs.IT↗