Localized Multidirectional Correction improves non-refusal target-response behavior in foundation models.
problem Controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models.
method Introduce Localized Multidirectional Correction (LoMC), a support-gated intervention framework.
result Substantially improves non-refusal target-response behavior while maintaining general capability under a compact intervention footprint.
New method estimates extreme outcomes in heavy-tailed data, breaking circular dependence.
problem Estimating outcomes for extreme events in heavy-tailed data.
method Proposes an ADRF estimator that includes a structured tail-shape output and a diagnostic to evaluate tail shape.
result Successfully reduces MAE in deep-tail and conditional-shortfall predictions.
LLM sandbox and persona dynamics create unethical reality gaps that shift risk to users.
problem Ethical issues arise from LLMs generating reality gaps that shift risk to uninformed users.
method Analyzes the ethical implications of LLM sandbox and persona dynamics, comparing them to financial regulation and compliance.
result Active generation of reality gaps is unethical as it shifts epistemic risk to users.
ELS framework improves safety alignment by dynamically steering LLMs towards helpful responses.
problem Over-Refusal in Aligned Large Language Models
method Fine-tuning free framework using an Energy-Based Model (EBM) to dynamically steer LLMs during inference.
result Extensive experiments show a significant reduction in false refusals (from 57.3% to 82.6%) while maintaining safety performance.
New benchmark uncovers hidden biases in LLMs that refuse to answer certain queries.
problem Evaluating fairness in LLMs, especially in sensitive applications.
method Silenced Bias Benchmark (SBB) using activation steering to reduce model refusals during QA.
result Exposes hidden unfair preferences in LLMs' latent space, distinguishing direct responses from underlying fairness issues.
Deleting refusal directions from models leads to systematically more optimistic decisions.
problem The impact of removing refusal directions from models on decision-making outcomes.
method Ablation study using a frozen pipeline of 21,600 weekly equity decisions.
result Ablation of refusal directions makes models more optimistic and justifies themselves more, but also reduces confidence.
Paper explores MM strategies that can refuse to quote or provide single-sided quotes.
problem Overcoming risks in market making due to changing market conditions.
method Adversarial reinforcement learning with new MM agent designs.
result Refusal to quote or providing single-sided quotes can improve MM performance.
LLM safety alignment explained as divergence estimation.
problem Aligning large language models to avoid harmful outputs.
method Presented a theoretical framework showing alignment methods as divergence estimators.
result KLDO method improves safety alignment using compliance-refusal datasets.
Training models to prefer certain responses can unintentionally shift probability to harmful ones.
problem Likelihood displacement in DPO models, leading to unintended unalignment.
method Characterized and mitigated likelihood displacement using CHES score.
result Training models to prefer certain responses can unintentionally shift probability mass to harmful responses.
A new method suppresses echo more effectively with lower latency.
problem Echo cannot be fully removed by linear filters due to nonlinear relationships.
method Uses a modified Conv-TasNet with multiple streams of input signals.
result Efficacy validated in both single-talk and double-talk situations.
Contrastive learning struggles with class collapse and feature suppression, revealing bias towards simpler solutions.
problem Contrastive learning struggles with class collapse and feature suppression, especially in supervised and unsupervised settings.
method Unified theoretical framework to determine which features are learnt by CL, revealing bias towards simpler solutions.
result Bias towards simpler solutions is a key factor in class collapse and feature suppression.
A new constructivist approach to modeling in economics and theory of consciousness is proposed. The state of elementary object is defined as a set of its measurable consumer properties. A proprietor's refusal or consent for the offered transaction is considered as a result of elementary economic measurement. We were al…
Paper proposes a statistical model for detecting mu-suppression in EEG signals.
problem Detecting mu-suppression in motor imagery EEG signals.
method Proposes a statistical model based on the generalized extreme value distribution (GEV) and a linear classifier.
result Preliminary results show good classification accuracy in detecting mu-suppression and distinguishing EEG events.
Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, which makes it challenging to deploy them in real-world safety-critical applications. In this paper, we conjecture that the leading cause of adversarial vulnerabili…
Deep-neural-network (DNN) based noise suppression systems yield significant improvements over conventional approaches such as spectral subtraction and non-negative matrix factorization, but do not generalize well to noise conditions they were not trained for. In comparison to DNNs, humans show remarkable noise suppress…
Contrastive learning properties studied, including feature suppression and hierarchical learning.
problem Feature suppression and hierarchical learning in contrastive learning.
method Generalized contrastive loss, instance-based contrastive learning, explicit and controllable competing features.
result Contrastive learning can suppress and prevent the learning of competing features.
Stochastic gradient descent updates parameters with summation gradient computed from a random data batch. This summation will lead to unbalanced training process if the data we obtained is unbalanced. To address this issue, this paper takes the error variance and error mean both into consideration. The adaptively adjus…
Suppressing bones on chest X-rays such as ribs and clavicle is often expected to improve pathologies classification. These bones can interfere with a broad range of diagnostic tasks on pulmonary disease except for musculoskeletal system. Current conventional method for acquisition of bone suppressed X-rays is dual ener…
Machine learning algorithms can unintentionally discriminate; tools detect and fix this.
problem Unintentional discrimination in machine learning algorithms.
method Statistical tools to detect and eliminate biases.
result Tools can identify and mitigate algorithmic discrimination.
Weak form of the Efficiency Market Hypothesis (EMH) excludes predictions of future market movements from historical data and makes the technical analysis (TA) out of law. However the technical analysis is widely used by traders and speculators who steadely refuse to consider the market as a "fair game" and survive with…
DG separates successes and failures by gating updates with advantage and surprisal.
problem Negative learning from surprising data in distributed reinforcement learning.
method DG gates each update with the product of advantage and surprisal, suppressing failures and preserving successes.
result DG outperforms other methods in various challenging reinforcement learning tasks.
New method improves fairness in DP learning by preventing excessive gradient suppression.
problem Disparate impact on model predictions for minority groups in DP learning.
method Bounded adaptive clipping to prevent excessive gradient suppression.
result Improves worst-class accuracy by over 10 percentage points compared to existing methods.
This paper addresses image classification through learning a compact and discriminative dictionary efficiently. Given a structured dictionary with each atom (columns in the dictionary matrix) related to some label, we propose cross-label suppression constraint to enlarge the difference among representations for differe…
New method improves autofocus in CBCT scans by 93%.
problem Improper geometry information leads to misplaced signals in CBCT.
method Learning-based motion estimation combined with CBCT consistency constraint.
result Average artifact suppression of 93% achieved.
In this paper we present detailed simulation results on the wealth distribution model with quenched saving propensities. Unlike other wealth distribution models where the saving propensities are either zero or constant, this model is not found to be ergodic and self-averaging. The wealth distribution statistics with a …
Model shows bailout stigma affects firm funding and market performance.
problem Bailout stigma impacts firm funding and market stability.
method Developed a model to analyze the effects of bailout stigma on firms and markets.
result Firms avoid stigma by withdrawing or refusing bailouts, leading to market freeze or revival.
Recurrent neural networks are known for their notorious exploding and vanishing gradient problem (EVGP). This problem becomes more evident in tasks where the information needed to correctly solve them exist over long time scales, because EVGP prevents important gradient components from being back-propagated adequately …
Bayesian method suppresses low-frequency pulses in audio recordings.
problem Suppressing long pulses caused by mechanical defects in audio recordings.
method Bayesian approach using Gaussian Process for pulse location, signal interpolation, and tail estimation.
result Perceptual results similar to previous methods, performs well on naturally degraded signals.
Improved market state classification for risk assessment.
problem Classifying financial market states for better risk assessment.
method Modified selection criteria for market states, clustering optimization, and visualization of correlation matrices.
result Statistically significant results in SP 500 and Nikkei 225 markets.
A new constructivist approach to modeling in economics and theory of consciousness is proposed. The state of elementary object is defined as a set of its measurable consumer properties. A proprietor's refusal or consent for the offered transaction is considered as a result of elementary economic measurement. Elementary…
DDGM generates realistic ECG signals for clinical use.
problem Generating accurate ECG signals from noisy data.
method Bayesian ECG reconstruction using DDGM trained on healthy ECG data.
result DDGM successfully generates realistic ECG signals for clinical applications.
Regularization methods can overregulate, suppressing causal features.
problem Mitigating shortcuts in models exploiting spurious correlations.
method Analysis of regularization methods and their effects on causal features.
result Regularization can overregulate, suppressing causal features.
New methods validate a hypothesis explaining how neural nets generalize well.
problem Why over-parameterized nets generalize well despite memorizing training data.
method Developed new algorithms to suppress weak gradient directions without per-example gradients.
result Validated a hypothesis about gradient directions and their role in generalization.
Donoho's JCGS (in press) paper is a spirited call to action for statisticians, who he points out are losing ground in the field of data science by refusing to accept that data science is its own domain. (Or, at least, a domain that is becoming distinctly defined.) He calls on writings by John Tukey, Bill Cleveland, and…
M2M tackles zero-shot structured noise suppression in images.
problem Structured noise with strong anisotropic correlations in real-world images.
method M2M introduces a novel sampling strategy that generates pseudo-independent sub-image pairs from a single noisy input, using directional interpolation and generalized median filtering.
result M2M consistently outperforms state-of-the-art zero-shot methods under correlated noise.
SNAP improves robust computation by emphasizing trustworthy items and downweighting outliers.
problem Improving robustness in computation, especially in high-dimensional settings.
method SNAP assigns weights based on mutual agreement, suppressing outlier contributions.
result SNAP ensures outliers contribute negligibly to computations, even in high-dimensional settings.
Robust STAP with coprime arrays reduces clutter using sparse modeling.
problem Limited performance due to training samples support in practical applications.
method Two-stage approach: 1) RD virtual snapshot, 2) RD sparse measurement modeling with OMP-like recovery.
result Robust to prior knowledge errors, good clutter suppression performance.
Noise can affect the overparametrization of QNNs, enabling new directions but also suppressing sensitivity.
problem The overparametrization of QNNs in the presence of noise.
method Analyzing the Quantum Fisher Information Matrix (QFIM) to understand how noise affects the rank of QFIM.
result Noise can turn previously-zero eigenvalues of the QFIM to non-zero, enabling exploration of new directions.
New approach to QFT divergences uses curved momentum space.
problem UV divergences in quantum field theory.
method Geodesic metric in curved momentum space.
result Intrinsic suppression of high-energy divergences.
Valid certifies LLMs' domain adherence, bounding out-of-domain behavior.
problem Adversarial susceptibility of LLMs to generate out-of-domain outputs.
method VALID approach providing adversarial bounds as a certificate.
result Validates LLMs' domain adherence with meaningful certificates.
Neuro-symbolic traders suppress market prices, highlighting risks to stability.
problem Understanding and quantifying the influence of AI-generated financial models on markets.
method Developed virtual neuro-symbolic traders using deep generative models and tested them in a virtual market.
result Neuro-symbolic traders suppress market prices compared to historical data, indicating potential market instability.
A simple method for estimating PMF on large supports, preserving structure and suppressing noise.
problem Nonparametric estimation of multi-modal, heavy-tailed PMF on large discrete support.
method Data-dependent low-pass filtering on a line graph Laplacian.
result Smooth, multi-modal estimate of PMF that preserves coarse structure and suppresses noise.
Study examines strategies to reduce volatility in leveraged ETF markets.
problem Rebalancing trades in leveraged ETFs can destabilize financial markets.
method Agent-based simulation to compare different trading strategies.
result Increasing the minimum number of orders in rebalancing trades reduces market volatility.
PatternLocal improves XAI for non-linear models by suppressing suppressor variables.
problem Suppressor variables cause false-positive feature attributions in non-linear models.
method PatternLocal uses locally linear surrogate models and transforms weights into a generative representation.
result PatternLocal reduces false-positive attributions and provides more reliable explanations.
Class incremental learning refers to a special multi-class classification task, in which the number of classes is not fixed but is increasing with the continual arrival of new data. Existing researches mainly focused on solving catastrophic forgetting problem in class incremental learning. To this end, however, these m…
PEGR improves deep learning models' robustness against noisy data.
problem Learning signals from noisy data in deep learning models.
method Per-example gradient regularization (PEGR) to suppress noise.
result PEGR enhances test error and robustness against noise perturbations.
Study of focal-entropy for class-imbalanced classification.
problem Understanding the focal-loss in class-imbalanced settings.
method Distributional viewpoint and information-theoretic analysis of focal-entropy.
result Focal-entropy minimizer exists and departs from data distribution.
Universal adversarial patches prevent face detection in various frameworks.
problem Preventing face detection in state-of-the-art face detection systems.
method Investigated the phenomenon of patches that suppress face detection and proposed optimization-based approaches for automatic design.
result Universal adversarial patches can prevent face detection without introducing false positives.