Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult to discover because the agent cannot predict them a priori. We propose using oracle feedback to learn a predictive model of these blind spots to red…
On-device research index
arXiv research
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.
168,657 papers · 148 categories
Trend · papers per month
48 results for “blind spots”
CNNs can develop blind spots due to uneven padding in feature maps.
problem Spatial bias in convolutional networks leads to blind spots in certain tasks.
method Identified and analyzed the role of padding in convolutional networks, proposing solutions to mitigate bias.
result Mitigating spatial bias improves model accuracy, especially in tasks like small object detection.
The adversarial training procedure proposed by Madry et al. (2018) is one of the most effective methods to defend against adversarial examples in deep neural networks (DNNs). In our paper, we shed some lights on the practicality and the hardness of adversarial training by showing that the effectiveness (robustness on t…
A framework to quantify deployment risk in ML systems, especially for rare states.
problem Under-supported rare states in ML models lead to unreliable performance in unseen data.
method Blind-Spot Mass (B_n(tau)) using Good-Turing unseen-species estimation.
result Identifies and quantifies the risk of under-supported states in ML models.
The study reveals flaws in pruning criteria and proposes a new assumption for better filter selection.
problem Flaws in existing pruning criteria for CNNs.
method Empirical experiments and Convolutional Weight Distribution Assumption.
result The Convolutional Weight Distribution Assumption improves filter selection in pruning.
The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choicescs.CL
Decoding strategies often exclude human-like tokens, creating a detectable gap in generated text.
problem Decoding strategies exclude contextually appropriate but statistically rare tokens, creating a detectable gap in generated text.
method Analysis of 1.8 million texts across 8 language models, 5 decoding strategies, and 53 hyperparameter configurations.
result 8-18% of human-selected tokens fall outside typical truncation boundaries, indicating a detectable gap.
Theoretical model for iterative user discovery in recommender systems.
problem Iterative feedback loops in recommender systems and their biases.
method Theoretical framework to model system evolution and convergence properties.
result Theoretical bounds and convergence properties on user discovery and blind spots.
Deep neural networks (DNNs)-powered Electrocardiogram (ECG) diagnosis systems recently achieve promising progress to take over tedious examinations by cardiologists. However, their vulnerability to adversarial attacks still lack comprehensive investigation. The existing attacks in image domain could not be directly app…
This paper explains tax policy for crypto assets in a rapidly evolving tech landscape.
problem Rapid technological changes in crypto assets create regulatory and tax policy blind spots.
method Explains principles of crypto assets, their technology, and tax issues.
result Tax policies are lagging behind innovation in blockchain and crypto.
Serial problems can't be efficiently parallelized, affecting machine learning models.
problem Inefficiency of parallelization in inherently serial problems.
method Formalized distinction in complexity theory, demonstrated with diffusion models.
result Diffusion models cannot solve inherently serial problems.
Christoffel function characterizes the corruption a bounded-degree certificate cannot remove in robust halfspace learning.
problem Robust halfspace learning under malicious noise
method Sum-of-Squares degree of outlier-removal certificate
result Christoffel function bounds the corruption a bounded-degree certificate cannot remove
We introduce MosAIc, an interactive web app that allows users to find pairs of semantically related artworks that span different cultures, media, and millennia. To create this application, we introduce Conditional Image Retrieval (CIR) which combines visual similarity search with user supplied filters or "conditions". …
We describe a novel method for training high-quality image denoising models based on unorganized collections of corrupted images. The training does not need access to clean reference images, or explicit pairs of corrupted images, and can thus be applied in situations where such data is unacceptably expensive or impossi…
LemonadeBench evaluates LLMs' economic intuition through a simulated lemonade stand.
problem Evaluating LLMs' economic understanding and decision-making in simple markets.
method Simulated lemonade stand business to test LLMs' long-term planning and profit maximization.
result Models achieve profitability but exhibit local rather than global optimization.
Blind Descent avoids gradient issues, using a different learning approach.
problem Gradient issues like exploding and vanishing gradients.
method Does not use gradients to guide learning; instead, it is a more fundamental learning process.
result Gradient descent is a specific case of Blind Descent.
New kernel models multi-output Gaussian processes accurately.
problem Challenges in modelling cross-covariances for multiple-output Gaussian processes.
method Replaced Gaussian components with block components of finite bandwidth in spectral mixture kernel.
result First multi-output generalization of spectral mixture kernel that can approximate any stationary multi-output kernel to arbitrary precision.
New divergences improve score-based methods for multi-modal distributions.
problem Blindness problem in score-based divergences for multi-modal distributions.
method Proposed a new family of divergences to mitigate blindness.
result Improved performance in density estimation compared to traditional approaches.
New method solves blind inverse problems by optimizing both operator and image parameters.
problem Solving blind inverse problems with known forward operator.
method Parallel reverse diffusion guided by gradients from intermediate stages.
result State-of-the-art performance on blind deblurring and imaging through turbulence.
New risk measures for incomplete markets without lattice structures.
problem Risk measures on incomplete markets without lattice structures.
method Study of risk measures without lattice structures, focusing on tractable dual representations and solid superspaces.
result Existence of a tractable dual representation equivalent to a Fatou-like property, and extension theorems under certain conditions.
Recent advances in the estimation of deep directed graphical models and recurrent networks let us contribute to the removal of a blind spot in the area of probabilistc modelling of time series. The proposed methods i) can infer distributed latent state-space trajectories with nonlinear transitions, ii) scale to large d…
Explores security challenges of machine learning in real-world systems.
problem Vulnerabilities in machine learning models deployed in safety-critical systems.
method Broadens systems security view of ML vulnerabilities, identifies novel challenges, proposes mitigation suggestions.
result Highlights novel challenges and proposes mitigation strategies for securing ML systems.
Stock index futures trading impact on spot price volatility. The CSI 300 studied with a TGARCH modelq-fin.ST
TGARCH model shows CSI-300 futures reduce spot price volatility.
problem Impact of CSI-300 futures trading on spot price volatility.
method TGARCH model applied to CSI-300 index data.
result CSI-300 futures trading significantly reduces spot price volatility.
Paper addresses the disparity between sampled and mean representations in disentangled learning.
problem Disparity between sampled and mean representations in disentangled learning.
method Proposes a method to eliminate the disparity by proving and utilizing the relationship between total correlation of sampled and mean representations for multivariate normal distributions.
result Demonstrates that a factorized mean representation can have lower total correlation than the sampled representation.
We propose orthogonality as a necessary condition for disentangling aleatoric and epistemic uncertainty.
problem Jointly estimating aleatoric and epistemic uncertainty is problematic and non-trivial.
method We propose orthogonality as a necessary condition for disentanglement and construct UDE to measure orthogonality and consistency.
result Orthogonality and consistency are necessary and sufficient criteria for disentanglement.
Paper develops new spot regression estimators using candlesticks for asset pricing.
problem Estimation of spot betas in asset pricing and risk management.
method Develops a new estimation and inference framework for spot regressions using high-frequency candlesticks.
result The proposed candlestick-based estimators reduce estimation risk and achieve higher power in hypothesis testing.
SVAR-LiNGAM reveals causal order in crypto-asset markets.
problem Understanding the causal relationships between spot rates and crypto-assets.
method Applied SVAR-LiNGAM to analyze spot exchange rates and crypto-asset exchange rates.
result Causal order found: EUR_USD spot rate -> Bitcoin -> Ethereum -> Ripple.
Spatial blind source separation simplifies multivariate spatial prediction.
problem Predicting multivariate measurements at unobserved locations with spatial dependencies.
method Spatial blind source separation as a pre-processing tool compared to Cokriging and neural networks.
result Spatial blind source separation simplifies spatial prediction by avoiding cross-dependencies.
Study hot spots on warped product manifolds and infinite cones.
problem Analyzing hot spots on specific geometric structures.
method Examining solutions to the heat equation on warped product manifolds and infinite cones.
result Hot spots behavior on warped product manifolds and infinite cones determined.
We propose a solution to the image deconvolution problem where the convolution kernel or point spread function (PSF) is assumed to be only partially known. Small perturbations generated from the model are exploited to produce a few principal components explaining the PSF uncertainty in a high dimensional space. Unlike …
Hot spots conjecture proven for small eigenvalue domains.
problem Hot spots conjecture for hyperbolic planar domains with small eigenvalues.
method Proved a variant of Rauch's hot spots conjecture.
result Second Neumann Laplace eigenfunctions have no interior critical points on large convex domains.
Continuous Speech Keyword Spotting (CSKS) is the problem of spotting keywords in recorded conversations, when a small number of instances of keywords are available in training data. Unlike the more common Keyword Spotting, where an algorithm needs to detect lone keywords or short phrases like "Alexa", "Cortana", "Hi Al…
New insights into learning for blind inverse problems with theoretical guarantees.
problem Learning in blind inverse problems where both signal and operator are unknown.
method Data-driven approaches using Linear Minimum Mean Square Estimators (LMMSEs) with theoretical analysis.
result Established equivalences with Tikhonov-regularized formulations and derived finite-sample error bounds.
VERAFI improves financial AI by verifying calculations and compliance.
problem Financial AI systems generate errors and violations during reasoning.
method VERAFI combines dense retrieval, reranking, and automated reasoning policies.
result VERAFI achieves 94.7% factual correctness, 81% relative improvement.
DiffDenoise preserves fine structures in medical images using conditional diffusion models.
problem Medical image denoising often results in loss of fine structures.
method Conditional diffusion model with stabilized reverse sampling and supervised training.
result DiffDenoise outperforms state-of-the-art methods in medical image denoising.
This paper introduces the class of volatility modulated Lévy-driven Volterra (VMLV) processes and their important subclass of Lévy semistationary (LSS) processes as a new framework for modelling energy spot prices. The main modelling idea consists of four principles: First, deseasonalised spot prices can be modelled di…
Hybrid models forecast EPEC energy spot prices.
problem Forecasting energy spot prices in EPEC markets.
method Combining Naive, Fourier, ARMA/GARCH, mean-reversion, jump-diffusion, and RNN models.
result Improved accuracy in forecasting compared to individual models.
We revisit the Blind Deconvolution problem with a focus on understanding its robustness and convergence properties. Provable robustness to noise and other perturbations is receiving recent interest in vision, from obtaining immunity to adversarial attacks to assessing and describing failure modes of algorithms in missi…
Improved MF-DFA model analyzes precious metals market efficiency and multifractality.
problem Analyze price fluctuations in precious metals market.
method Proposed Bi-OSW-MF-DFA method compared to MF-DFA.
result Bi-OSW-MF-DFA method shows better efficiency in precious metals market analysis.
Deep convolutional network has been the state-of-the-art approach for a wide variety of tasks over the last few years. Its successes have, in many cases, turned it into the default model in quite a few domains. In this work, we will demonstrate that convolutional networks have limitations that may, in some cases, hinde…
Blind Polynomial Regressioneess.SP
Paper tackles blind polynomial regression for unknown inputs.
problem Fitting a polynomial to unknown or partially known input data.
method Formally defines the problem, proposes algorithmic approaches, and applies to jitter-correction.
result Proposes effective methods for blind polynomial regression.
The study proves constant-curvature analogues of hot spots conjecture for triangles.
problem Proving the hot spots conjecture in constant curvature domains.
method Analyzing geodesic triangles of constant negative curvature and using Killing fields.
result First mixed Dirichlet-Neumann Laplace eigenfunctions have no non-vertex critical points in constant curvature triangles.
New method uses single quantum state for machine learning tasks, improving accuracy.
problem Challenges in unsupervised learning with quantum data.
method SIngle-Preparation Quantum Information Processing (SIPQIP) concept.
result Significantly more accurate estimation compared to traditional methods.
In this paper we introduce a flexible HJM-type framework that allows for consistent modelling of intraday, spot, futures, and option prices. This framework is based on stochastic processes with economic interpretations and consistent with the initial term structure given in the form of a price forward curve. Furthermor…
Research forecasts electricity spot prices using stochastic volatility models.
problem Forecasting day-ahead electricity prices in a spot market.
method Exploring and enriching a baseline stochastic volatility model with exogenous regressors.
result A better fitting model confirmed by out-of-sample forecasts.
SpotV2Net forecasts intraday spot volatilities using graph attention networks.
problem Forecasting multivariate intraday spot volatilities accurately.
method Graph Attention Network architecture with Fourier estimates of spot and vol-of-vol volatilities.
result SpotV2Net outperforms other models in forecasting accuracy.
New method prevents RLHF alignment collapse by accounting for policy's influence on reward model updates.
problem Iterative RLHF leads to alignment collapse where policies exploit RM's blind spots.
method Foresighted policy optimization (FPO) restores missing steering term via regularization.
result FPO prevents alignment collapse on LLM alignment pipelines using Llama-3.2-1B.
Towards Unsupervised Single-Channel Blind Source Separation using Adversarial Pair Unmix-and-Remixeess.SP
Blind single-channel source separation is a long standing signal processing challenge. Many methods were proposed to solve this task utilizing multiple signal priors such as low rank, sparsity, temporal continuity etc. The recent advance of generative adversarial models presented new opportunities in signal regression …
Algorithm predicts with optimal loss by abstaining from uncertain test examples.
problem Predicting with training data not matching test data.
method Transductive abstention algorithm using labeled and unlabeled test examples.
result Optimal prediction loss guarantees with additional term for abstaining cost.