A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Study analyzes feedback complexity for sparse feature retrieval in deep networks.
Dynamic model pruning improves performance on deep neural networks without retraining.
Recent advances in deep neural networks (DNNs) owe their success to training algorithms that use backpropagation and gradient-descent. Backpropagation, while highly effective on von Neumann architectures, becomes inefficient when scaling to large networks. Commonly referred to as the weight transport problem, each neur…
We propose a method for solving statistical mechanics problems defined on sparse graphs. It extracts a small Feedback Vertex Set (FVS) from the sparse graph, converting the sparse system to a much smaller system with many-body and dense interactions with an effective energy on every configuration of the FVS, then learn…
This work explores non-negative low-rank matrix factorization based on regularized Poisson models (PF or "Poisson factorization" for short) for recommender systems with implicit-feedback data. The properties of Poisson likelihood allow a shortcut for very fast computations over zero-valued inputs, and oftentimes result…
We consider the problem of learning from sparse and underspecified rewards, where an agent receives a complex input, such as a natural language instruction, and needs to generate a complex response, such as an action sequence, while only receiving binary success-failure feedback. Such success-failure rewards are often …
Physics-informed GCRL tackles sparse feedback learning with hybrid dynamics.
Algorithm achieves comparable performance to fully dynamic data with only a few batches.
Multi-label network classification is a well-known task that is being used in a wide variety of web-based and non-web-based domains. It can be formalized as a multi-relational learning task for predicting nodes labels based on their relations within the network. In sparse networks, this prediction task can be very chal…
Deep reinforcement learning has obtained significant breakthroughs in recent years. Most methods in deep-RL achieve good results via the maximization of the reward signal provided by the environment, typically in the form of discounted cumulative returns. Such reward signals represent the immediate feedback of a partic…
Study shows reinforcement learning is possible with once-per-episode feedback.
Traditional collaborative filtering (CF) based recommender systems tend to perform poorly when the user-item interactions/ratings are highly scarce. To address this, we propose a learning framework that improves collaborative filtering with a synthetic feedback loop (CF-SFL) to simulate the user feedback. The proposed …
Proposes SSL framework for improving item recommendations in large-scale systems.
Combining simple elements from the literature, we define a linear model that is geared toward sparse data, in particular implicit feedback data for recommender systems. We show that its training objective has a closed-form solution, and discuss the resulting conceptual insights. Surprisingly, this simple model achieves…
IDS improves reinforcement learning with contextual information.
Semi-supervised method enhances recommendation from sparse data.
To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users. Moreover, they will need to learn these behaviors within a reasonable amount of time while efficiently leveraging the sparse feedback a human trainer is capable o…
A new method shapes reinforcement learning environments by abstracting large state spaces.
Variational Proximal Policy Optimization improves reinforcement learning from human feedback.
PopArt efficiently solves sparse linear bandits with tighter recovery guarantees.
The paper improves DFA for CNN and RNN training to match BP accuracy.
Learning goal-directed behavior in environments with sparse feedback is a major challenge for reinforcement learning algorithms. The primary difficulty arises due to insufficient exploration, resulting in an agent being unable to learn robust value functions. Intrinsically motivated agents can explore new behavior for …
The paper explores a Multi-Objective RL approach for trading that generalizes reward functions.
Learning optimal policies from sparse feedback is a known challenge in reinforcement learning. Hindsight Experience Replay (HER) is a multi-goal reinforcement learning algorithm that comes to solve such tasks. The algorithm treats every failure as a success for an alternative (virtual) goal that has been achieved in th…
Reinforcement learning usually uses the feedback rewards of environmental to train agents. But the rewards in the actual environment are sparse, and even some environments will not rewards. Most of the current methods are difficult to get good performance in sparse reward or non-reward environments. Although using shap…
Increased public interest in healthy lifestyles has motivated the study of algorithms that encourage people to follow a healthy diet. Applying collaborative filtering to build recommendation systems in domains where only implicit feedback is available is also a rapidly growing research area. In this report we combine t…
Improves content allocation in educational platforms with sparse data.
We consider the problem of estimating the parameters of a multivariate Bernoulli process with auto-regressive feedback in the high-dimensional setting where the number of samples available is much less than the number of parameters. This problem arises in learning interconnections of networks of dynamical systems with …
BCCP uses bandit feedback to provide reliable predictions with limited labeled data.
Efficiently poisons offline RLHF models by flipping preference labels.
Although deep learning has shown great success in recent years, researchers have discovered a critical flaw where small, imperceptible changes in the input to the system can drastically change the output classification. These attacks are exploitable in nearly all of the existing deep learning classification frameworks.…
New method reduces regret for sparse adversarial SSP problems.
With the growing importance of personalized recommendation, numerous recommendation models have been proposed recently. Among them, Matrix Factorization (MF) based models are the most widely used in the recommendation field due to their high performance. However, MF based models suffer from cold start problems where us…
EFS uses LLMs to optimize sparse portfolios by evolving alpha factors.
SIBRE boosts reinforcement learning convergence by rewarding improvement over past performance.
New approach improves cross-domain recommendation for sparse target domains.
In this paper, we apply a mini-batch based negative sampling method to efficiently train a latent factor autoencoder model on large scale and sparse data for implicit feedback collaborative filtering. We compare our work against a state-of-the-art baseline model on different experimental datasets and show that this met…
Transforming sparse outcomes into dense process rewards for efficient reinforcement learning.
DisCor corrects reinforcement learning issues by re-weighting collected data.
A new method for online prediction uncertainty quantification in non-exchangeable panel data.
Recommendation is the task of improving customer experience through personalized recommendation based on users' past feedback. In this paper, we investigate the most common scenario: the user-item (U-I) matrix of implicit feedback. Even though many recommendation approaches are designed based on implicit feedback, they…
Paper proposes RRD to learn proxy rewards for sparse delayed rewards in episodic reinforcement learning.
A new algorithm RTO integrates DPO and PPO for RLHF, improving performance.
Algorithm optimizes collaborative learning among distributed clients using kernel-based bandits.
Additive asynchronous and cyclostationary impulsive noise limits communication performance in OFDM powerline communication (PLC) systems. Conventional OFDM receivers assume additive white Gaussian noise and hence experience degradation in communication performance in impulsive noise. Alternate designs assume a parametr…
New insights into cascade feedback linearization of control systems.
New conditions show proxy data can improve policy learning in sparse expert data contexts.
New method learns from either positive or negative feedback alone.