In this paper, we study a fundamental problem in submodular optimization, which is called sequential submodular maximization. Specifically, we aim to select and rank a group of $k$ items from a ground set $V$ such that the weighted summation of $k$ (possibly non-monotone) submodular functions $f_1, \cdots ,f_k: 2^V \rightarrow \mathbb{R}^+$ is maximized, here each function $f_j$ takes the first $j$ items from this sequence as input. The existing research on sequential submodular maximization has predominantly concentrated on the monotone setting, assuming that the submodular functions are non-decreasing. However, in various real-world scenarios, like diversity-aware recommendation systems, adding items to an existing set might negatively impact the overall utility. In response, this paper pioneers the examination of the aforementioned problem with non-monotone submodular functions and offers effective solutions for both flexible and fixed length constraints, as well as a special case with identical utility functions. The empirical evaluations further validate the effectiveness of our proposed algorithms in the domain of video recommendations. The results of this research have implications in various fields, including recommendation systems and assortment optimization, where the ordering of items significantly impacts the overall value obtained.

Agents' learning from feedback shapes economic outcomes, and many economic decision-makers today employ learning algorithms to make consequential choices. This note shows that a widely used learning algorithm, $\varepsilon$-Greedy, exhibits emergent risk aversion: it prefers actions with lower variance. When presented with actions of the same expectation, under a wide range of conditions, $\varepsilon$-Greedy chooses the lower-variance action with probability approaching one. This emergent preference can have wide-ranging consequences, ranging from concerns about fairness to homogenization, and holds transiently even when the riskier action has a strictly higher expected payoff. We discuss two methods to correct this bias. The first method requires the algorithm to reweight data as a function of how likely the actions were to be chosen. The second requires the algorithm to have optimistic estimates of actions for which it has not collected much data. We show that risk-neutrality is restored with these corrections.

The increasing availability of Massive Open Online Courses (MOOCs) has created a necessity for personalized course recommendation systems. These systems often combine neural networks with Knowledge Graphs (KGs) to achieve richer representations of learners and courses. While these enriched representations allow more accurate and personalized recommendations, explainability remains a significant challenge which is especially problematic for certain domains with significant impact such as education and online learning. Recently, a novel class of recommender systems that uses reinforcement learning and graph reasoning over KGs has been proposed to generate explainable recommendations in the form of paths over a KG. Despite their accuracy and interpretability on e-commerce datasets, these approaches have scarcely been applied to the educational domain and their use in practice has not been studied. In this work, we propose an explainable recommendation system for MOOCs that uses graph reasoning. To validate the practical implications of our approach, we conducted a user study examining user perceptions of our new explainable recommendations. We demonstrate the generalizability of our approach by conducting experiments on two educational datasets: COCO and Xuetang.

We consider the problem of building an assistive robotic system that can help humans in daily household cleanup tasks. Creating such an autonomous system in real-world environments is inherently quite challenging, as a general solution may not suit the preferences of a particular customer. Moreover, such a system consists of multi-objective tasks comprising -- (i) Detection of misplaced objects and prediction of their potentially correct placements, (ii) Fine-grained manipulation for stable object grasping, and (iii) Room-to-room navigation for transferring objects in unseen environments. This work systematically tackles each component and integrates them into a complete object rearrangement pipeline. To validate our proposed system, we conduct multiple experiments on a real robotic platform involving multi-room object transfer, user preference-based placement, and complex pick-and-place tasks. Project page: https://sites.google.com/eng.ucsd.edu/home-robot

Neural network approaches in recommender systems have shown remarkable success by representing a large set of items as a learnable vector embedding table. However, infrequent items may suffer from inadequate training opportunities, making it difficult to learn meaningful representations. We examine that in attribute and context-aware settings, the poorly learned embeddings of infrequent items impair the recommendation accuracy. To address such an issue, we propose a proxy-based item representation that allows each item to be expressed as a weighted sum of learnable proxy embeddings. Here, the proxy weight is determined by the attributes and context of each item and may incorporate bias terms in case of frequent items to further reflect collaborative signals. The proxy-based method calculates the item representations compositionally, ensuring each representation resides inside a well-trained simplex and, thus, acquires guaranteed quality. Additionally, that the proxy embeddings are shared across all items allows the infrequent items to borrow training signals of frequent items in a unified model structure and end-to-end manner. Our proposed method is a plug-and-play model that can replace the item encoding layer of any neural network-based recommendation model, while consistently improving the recommendation performance with much smaller parameter usage. Experiments conducted on real-world recommendation benchmark datasets demonstrate that our proposed model outperforms state-of-the-art models in terms of recommendation accuracy by up to 17% while using only 10% of the parameters.

Algorithmic recommender systems such as Spotify and Netflix affect not only consumer behavior but also producer incentives. Producers seek to create content that will be shown by the recommendation algorithm, which can impact both the diversity and quality of their content. In this work, we investigate the resulting supply-side equilibria in personalized content recommender systems. We model users and content as $D$-dimensional vectors, the recommendation algorithm as showing each user the content with highest dot product, and producers as maximizing the number of users who are recommended their content minus the cost of production. Two key features of our model are that the producer decision space is multi-dimensional and the user base is heterogeneous, which contrasts with classical low-dimensional models. Multi-dimensionality and heterogeneity create the potential for specialization, where different producers create different types of content at equilibrium. Using a duality argument, we derive necessary and sufficient conditions for whether specialization occurs: these conditions depend on the extent to which users are heterogeneous and to which producers can perform well on all dimensions at once without incurring a high cost. Then, we characterize the distribution of content at equilibrium in concrete settings with two populations of users. Lastly, we show that specialization can enable producers to achieve positive profit at equilibrium, which means that specialization can reduce the competitiveness of the marketplace. At a conceptual level, our analysis of supply-side competition takes a step towards elucidating how personalized recommendations shape the marketplace of digital goods, and towards understanding what new phenomena arise in multi-dimensional competitive settings.

Machine learning training data is often dynamic in real-world use cases, i.e., data is added or removed and may experience distribution shifts over time. Models must incorporate this evolving training data to improve generalization, adapt to potential distribution shifts, and adhere to privacy regulations. However, the cost of model (re)training is proportional to how often the model trains and on how much data it trains on. While ML research explores these topics in isolation, there is no end-to-end open-source platform to facilitate the exploration of model retraining and data selection policies and the deployment these algorithms efficiently at scale. We present Modyn, a platform for model training on dynamic datasets that enables sample-level data selection and triggering policies. Modyn orchestrates continuous training pipelines while optimizing the underlying system infrastructure to support fast access to arbitrary data samples for efficient data selection. Modyn's extensible architecture allows users to run training pipelines without modifying the platform code, and enables researchers to effortlessly extend the system. We evaluate Modyn's training throughput, showing that even in memory-bound recommendation systems workloads, Modyn is able to reach 80 to 100 % of the throughput compared to loading big chunks of data locally without sample-level data selection. Additionally, we showcase Modyn's functionality with three different data selection policies.

How to Do It is Slate's sex advice column. Send it to Stoya and Rich here. I'm in a long-term relationship that's been satisfying emotionally, mentally, and sexually. We explore and try new things, I feel cared for and loved. The problem is this new hobby I've developed that I haven't shared and can't seem to stop.

Hosting about 50 million songs and 4 billion playlists, there is an enormous amount of data generated at Spotify every single day - upwards of 600 gigabytes of data (harvard.edu). Since the algorithms that Spotify uses in recommendation systems is proprietary and confidential, code for big data analytics and recommendation can only be speculated. However, it is widely theorized that Spotify uses two main strategies to target users' playlists and personalized mixes that are infamous for their retention - exploration and exploitation (kaggle.com). This paper aims to appropriate the filtering using the approach of deep learning for maximum user likeability. The architecture achieves 98.57% and 80% training and validation accuracy respectively.

Many high-stake decisions follow an expert-in-loop structure in that a human operator receives recommendations from an algorithm but is the ultimate decision maker. Hence, the algorithm's recommendation may differ from the actual decision implemented in practice. However, most algorithmic recommendations are obtained by solving an optimization problem that assumes recommendations will be perfectly implemented. We propose an adherence-aware optimization framework to capture the dichotomy between the recommended and the implemented policy and analyze the impact of partial adherence on the optimal recommendation. We show that overlooking the partial adherence phenomenon, as is currently being done by most recommendation engines, can lead to arbitrarily severe performance deterioration, compared with both the current human baseline performance and what is expected by the recommendation algorithm. Our framework also provides useful tools to analyze the structure and to compute optimal recommendation policies that are naturally immune against such human deviations, and are guaranteed to improve upon the baseline policy.