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.
Binary Neural Networks (BNNs) have been garnering interest thanks to their compute cost reduction and memory savings. However, BNNs suffer from performance degradation mainly due to the gradient mismatch caused by binarizing activations. Previous works tried to address the gradient mismatch problem by reducing the disc…
We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the distribution of states visited under the behavior policy used to collect data, and what …
New techniques improve distributed training with compressed gradients.
AIS corrects rollout-training mismatch in quantized RL, improving speed and stability.
New method uses surrogate gradients to train efficient spiking networks on neuromorphic hardware.
A new method improves data generation quality by correcting score mismatches.
Off-policy deep reinforcement learning (RL) algorithms are incapable of learning solely from batch offline data without online interactions with the environment, due to the phenomenon known as \textit{extrapolation error}. This is often due to past data available in the replay buffer that may be quite different from th…
AdvAs improves GAN training by penalizing the generator based on discriminator gradients.
SA-PEF improves federated learning efficiency by correcting gradient mismatches.
We study how the behavior of deep policy gradient algorithms reflects the conceptual framework motivating their development. To this end, we propose a fine-grained analysis of state-of-the-art methods based on key elements of this framework: gradient estimation, value prediction, and optimization landscapes. Our result…
Large learning rates improve kernel method performance.
New framework for RL transfer learning with state-action mismatch.
New method optimizes language model performance for test-time strategies.
AdaGrad fails to adapt to Hölder-smoothness in composite optimization problems.
New algorithm reduces performance loss in IRL with mismatched transition dynamics.
Dynamic Vocabulary Pruning stabilizes LLM training by removing low-probability tokens.
This paper considers the classification of linear subspaces with mismatched classifiers. In particular, we assume a model where one observes signals in the presence of isotropic Gaussian noise and the distribution of the signals conditioned on a given class is Gaussian with a zero mean and a low-rank covariance matrix.…
New algorithm optimizes PAC-Bayes bound without surrogate loss.
The paper addresses score-mismatched diffusion models and zero-shot conditional samplers.
Thompson Sampling shows polynomial regret for combinatorial semi-bandits with subgaussian rewards.
New method addresses error bounds for PnP-ULA under mismatched models.
Paper addresses linear regression with partially mismatched data using local search with theoretical guarantees.
Constructing VAE Latent Spaces with Prescribed Topology
PACMAN provides bounds for classification tasks considering accuracy vs. negative log-loss mismatch.
Current approaches for Knowledge Distillation (KD) either directly use training data or sample from the training data distribution. In this paper, we demonstrate effectiveness of 'mismatched' unlabeled stimulus to perform KD for image classification networks. For illustration, we consider scenarios where this is a comp…
Study on LMMSE estimation with model mismatch, quantifying MSE trade-offs.
Hamiltonian Monte Carlo (HMC) is a popular Markov chain Monte Carlo (MCMC) algorithm that generates proposals for a Metropolis-Hastings algorithm by simulating the dynamics of a Hamiltonian system. However, HMC is sensitive to large time discretizations and performs poorly if there is a mismatch between the spatial geo…
Model-based reinforcement learning (MBRL) has been shown to be a powerful framework for data-efficiently learning control of continuous tasks. Recent work in MBRL has mostly focused on using more advanced function approximators and planning schemes, with little development of the general framework. In this paper, we id…
We identity a by-far-unrecognized problem of Adam-style optimizers which results from unnecessary coupling between momentum and adaptivity. The coupling leads to instability and divergence when the momentum and adaptivity parameters are mismatched. In this work, we propose a method, Laprop, which decouples momentum and…
The representation of the approximate posterior is a critical aspect of effective variational autoencoders (VAEs). Poor choices for the approximate posterior have a detrimental impact on the generative performance of VAEs due to the mismatch with the true posterior. We extend the class of posterior models that may be l…
Supervised learning based on a deep neural network recently has achieved substantial improvement on speech enhancement. Denoising networks learn mapping from noisy speech to clean one directly, or to a spectrum mask which is the ratio between clean and noisy spectra. In either case, the network is optimized by minimizi…
A conservative drifting method improves generative modeling by using KDE gradients, proving convergence rates.
Recently, there has been significant interest in linear regression in the situation where predictors and responses are not observed in matching pairs corresponding to the same statistical unit as a consequence of separate data collection and uncertainty in data integration. Mismatched pairs can considerably impact the …
Ensemble models improve prediction calibration for mismatched distributions.
A new multi-agent learning method improves performance in complex games.
Study on thermodynamic costs of simple linear regression.
The dictionary-aided sparse regression (SR) approach has recently emerged as a promising alternative to hyperspectral unmixing (HU) in remote sensing. By using an available spectral library as a dictionary, the SR approach identifies the underlying materials in a given hyperspectral image by selecting a small subset of…
Empirical study compares finite- and infinite-width BNNs, revealing performance differences under model mismatch.
We characterize the performance of sequential information guided sensing, Info-Greedy Sensing, when there is a mismatch between the true signal model and the assumed model, which may be a sample estimate. In particular, we consider a setup where the signal is low-rank Gaussian and the measurements are taken in the dire…
When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference. For example, in sequence-to-sequence modeling we are interested in high-quality translated sentences, but training typically uses maximum likelihood at the word level. The…
The performance of automatic speech recognition (ASR) systems can be significantly compromised by previously unseen conditions, which is typically due to a mismatch between training and testing distributions. In this paper, we address robustness by studying domain invariant features, such that domain information become…
Many sleep studies suffer from the problem of insufficient data to fully utilize deep neural networks as different labs use different recordings set ups, leading to the need of training automated algorithms on rather small databases, whereas large annotated databases are around but cannot be directly included into thes…
New -step policy gradient method avoids local optima in restricted policy classes.
In this study, we consider classification problems based on neural networks in data-imbalanced environment. Learning from an imbalanced data set is one of the most important and practical problems in the field of machine learning. A weighted loss function based on cost-sensitive approach is a well-known effective metho…
Most of the existing studies on voice conversion (VC) are conducted in acoustically matched conditions between source and target signal. However, the robustness of VC methods in presence of mismatch remains unknown. In this paper, we report a comparative analysis of different VC techniques under mismatched conditions. …
New algorithm solves Schrödinger bridge problem with mismatched channels.
Paper proposes FPG algorithm for unbiased off-policy PG estimation.
Study OOD generalization in meta-reinforcement learning using information theory.