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.
ADER addresses continual learning in session-based recommendation by periodically replaying exemplars with adaptive distillation.
This paper tackles federated incremental learning with dynamic memory allocation for improved model performance in non-IID data.
Exemplar VAEs link generative models with nearest neighbor retrieval and data augmentation.
EASE optimizes exemplar selection for ICL in LLMs efficiently.
Efficiently preserves old class knowledge in memory-limited settings.
We propose a framework for synthesis of geological images based on an exemplar image. We synthesize new realizations such that the discrepancy in the patch distribution between the realizations and the exemplar image is minimized. Such discrepancy is quantified using a kernel method for two-sample test called maximum m…
Paper proposes mnemonics framework for MCIL without forgetting.
Proposes a framework for generating explainable AI exemplars.
Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize a rule-based replay strategy, which may be sub-optimal. In this work, we consid…
This paper introduces a novel approach to in-painting where the identity of the object to remove or change is preserved and accounted for at inference time: Exemplar GANs (ExGANs). ExGANs are a type of conditional GAN that utilize exemplar information to produce high-quality, personalized in painting results. We propos…
New modifiers improve noisy RNN replay in hippocampal networks.
New insights into experience replay in RL algorithms.
This project combines recent advances in experience replay techniques, namely, Combined Experience Replay (CER), Prioritized Experience Replay (PER), and Hindsight Experience Replay (HER). We show the results of combinations of these techniques with DDPG and DQN methods. CER always adds the most recent experience to th…
We present a new replay-based method of continual classification learning that we term "conditional replay" which generates samples and labels together by sampling from a distribution conditioned on the class. We compare conditional replay to another replay-based continual learning paradigm (which we term "marginal rep…
This paper describes an improvement in Deep Q-learning called Reverse Experience Replay (also RER) that solves the problem of sparse rewards and helps to deal with reward maximizing tasks by sampling transitions successively in reverse order. On tasks with enough experience for training and enough Experience Replay mem…
Curious Replay improves model-based reinforcement learning agents' adaptability.
A new method prioritizes and recycles experiences for better reinforcement learning.
ReaPER improves learning efficiency by prioritizing reliable experiences.
Unified study of stateful replay for streaming learning, reducing forgetting by 2-3x.
In this paper, we propose a replay attack spoofing detection system for automatic speaker verification using multitask learning of noise classes. We define the noise that is caused by the replay attack as replay noise. We explore the effectiveness of training a deep neural network simultaneously for replay attack spoof…
Generative replay improves continual learning by using generated data as negative examples.
A method for collecting human supervision that combines rules and instance labels.
The paper improves reinforcement learning stability and efficiency with a new theoretical framework.
Exemplar-based clustering methods have been shown to produce state-of-the-art results on a number of synthetic and real-world clustering problems. They are appealing because they offer computational benefits over latent-mean models and can handle arbitrary pairwise similarity measures between data points. However, when…
We present a generative framework for generalized zero-shot learning where the training and test classes are not necessarily disjoint. Built upon a variational autoencoder based architecture, consisting of a probabilistic encoder and a probabilistic conditional decoder, our model can generate novel exemplars from seen/…
In this paper, we consider the problem of selecting representatives from a data set for arbitrary supervised/unsupervised learning tasks. We identify a subset of a data set such that 1) the size of is much smaller than and 2) efficiently describes the entire data set, in a way formalized via convex …
A new method improves continual learning by replaying pseudo data and using orthogonal weight modification.
Our work is a simple extension of the paper "Exploration by Random Network Distillation". More in detail, we show how to efficiently combine Intrinsic Rewards with Experience Replay in order to achieve more efficient and robust exploration (with respect to PPO/RND) and consequently better results in terms of agent perf…
Experience replay is widely used in deep reinforcement learning algorithms and allows agents to remember and learn from experiences from the past. In an effort to learn more efficiently, researchers proposed prioritized experience replay (PER) which samples important transitions more frequently. In this paper, we propo…
Prototype-based generative replay framework for online continual regression.
New framework models echo chamber learning, proving tight bounds on algorithm performance.
We investigate the combination of actor-critic reinforcement learning algorithms with uniform large-scale experience replay and propose solutions for two challenges: (a) efficient actor-critic learning with experience replay (b) stability of off-policy learning where agents learn from other agents behaviour. We employ …
Metric learning methods for dimensionality reduction in combination with k-Nearest Neighbors (kNN) have been extensively deployed in many classification, data embedding, and information retrieval applications. However, most of these approaches involve pairwise training data comparisons, and thus have quadratic computat…
Explicit high-order feature interactions efficiently capture essential structural knowledge about the data of interest and have been used for constructing generative models. We present a supervised discriminative High-Order Parametric Embedding (HOPE) approach to data visualization and compression. Compared to deep emb…
Experience replay is a key technique behind many recent advances in deep reinforcement learning. Allowing the agent to learn from earlier memories can speed up learning and break undesirable temporal correlations. Despite its wide-spread application, very little is understood about the properties of experience replay. …
An important component of many Deep Reinforcement Learning algorithms is the Experience Replay which serves as a storage mechanism or memory of made experiences. These experiences are used for training and help the agent to stably find the perfect trajectory through the problem space. The classic Experience Replay howe…
With the growing interest on Network Analysis, Relational Data Mining is becoming an emphasized domain of Data Mining. This paper addresses the problem of extracting representative elements from a relational dataset. After defining the notion of degree of representativeness, computed using the Borda aggregation procedu…
Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the accuracy of such updates may deteriorate when the policy diverges from past behavio…
LiDER refreshes past experiences in RL by dreaming about them.
For a certain class of distributions, we prove that the linear programming relaxation of -medoids clustering---a variant of -means clustering where means are replaced by exemplars from within the dataset---distinguishes points drawn from nonoverlapping balls with high probability once the number of points drawn a…
RER improves sample complexity by updating in reverse order.
Modern Hopfield networks help prevent forgetting in generative models after task changes.
Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting has gained attention recently as a natural setting that is difficult to tackle. Me…
Improves sparse reinforcement learning efficiency with OYMB.
ER-GNN uses experience replay to prevent GNNs from forgetting previous tasks.
We examine the question of when and how parametric models are most useful in reinforcement learning. In particular, we look at commonalities and differences between parametric models and experience replay. Replay-based learning algorithms share important traits with model-based approaches, including the ability to plan…
Improved RA detection with SNN outperforming baseline by 26.8% EER.
VRER selectively reuses past observations to reduce variance in policy optimization.