How to Lead When You Can’t See the Way
An HBR Executive Masterclass with HBS professor Linda Hill on how to steer the ship even when you can’t see through the fog.
Like
0
Liked
Liked
digitado
About digitado
Posts by :
What Does Flow Matching Bring To TD Learning?
Recent work shows that flow matching can be effective for scalar Q-value function estimation in reinforcement learning (RL), but it remains unclear why or how this approach differs from standard critics. Contrary to conventional belief, we show that their success is not explained by distributional RL, as explicitly modeling return distributions can reduce performance. Instead, we argue that the use of integration for reading out values and dense velocity supervision at each step of this integration process for […]
Like
0
Liked
Liked
PTOPOFL: Privacy-Preserving Personalised Federated Learning via Persistent Homology
Federated learning (FL) faces two structural tensions: gradient sharing enables data-reconstruction attacks, while non-IID client distributions degrade aggregation quality. We introduce PTOPOFL, a framework that addresses both challenges simultaneously by replacing gradient communication with topological descriptors derived from persistent homology (PH). Clients transmit only 48-dimensional PH feature vectors-compact shape summaries whose many-to-one structure makes inversion provably ill-posed-rather than model gradients. The server performs topology-guided personalised aggregation: clients are clustered by Wasserstein similarity between their PH diagrams, intra-cluster models […]
Like
0
Liked
Liked
Anti-patterns: things to avoid
Agentic Engineering Patterns > There are some behaviors that are anti-patterns in our weird new world of agentic engineering. Inflicting unreviewed code on collaborators This anti-pattern is common and deeply frustrating. Don’t file pull requests with code you haven’t reviewed yourself. If you open a PR with hundreds (or thousands) of lines of code that an agent produced for you, and you haven’t done the work to ensure that code is functional yourself, you are delegating the actual […]
Like
0
Liked
Liked
The US military is still using Claude — but defense-tech clients are fleeing
As the US continues its aerial attack on Iran, Anthropic models are being used for many targeting decisions.
Like
0
Liked
Liked
Bayesian Modeling of Collatz Stopping Times: A Probabilistic Machine Learning Perspective
We study the Collatz total stopping time $τ(n)$ over $nle 10^7$ from a probabilistic machine learning viewpoint. Empirically, $τ(n)$ is a skewed and heavily overdispersed count with pronounced arithmetic heterogeneity. We develop two complementary models. First, a Bayesian hierarchical Negative Binomial regression (NB2-GLM) predicts $τ(n)$ from simple covariates ($log n$ and residue class $n bmod 8$), quantifying uncertainty via posterior and posterior predictive distributions. Second, we propose a mechanistic generative approximation based on the odd-block decomposition: for odd […]
Like
0
Liked
Liked
**Used RL to solve a healthcare privacy problem that static NLP pipelines can’t handle**
Most de-identification tools are stateless. They scan a document, remove identifiers, done. No memory of what came before, no awareness of risk accumulating over time. That works fine for isolated records. It breaks down in streaming systems where the same patient appears across hundreds of events over time. I framed this as a control problem instead. The system maintains a per-subject exposure state and computes rolling re-identification risk as new events arrive. When risk crosses a threshold, the […]
Like
0
Liked
Liked
IPD: Boosting Sequential Policy with Imaginary Planning Distillation in Offline Reinforcement Learning
Decision transformer based sequential policies have emerged as a powerful paradigm in offline reinforcement learning (RL), yet their efficacy remains constrained by the quality of static datasets and inherent architectural limitations. Specifically, these models often struggle to effectively integrate suboptimal experiences and fail to explicitly plan for an optimal policy. To bridge this gap, we propose textbf{Imaginary Planning Distillation (IPD)}, a novel framework that seamlessly incorporates offline planning into data generation, supervised training, and online inference. Our framework […]
Like
0
Liked
Liked
Google Pixel 10a review: The sidegrade
Google’s budget Pixels have long been a top recommendation for anyone who needs a phone with a good camera and doesn’t want to pay flagship prices. This year, Google’s A-series Pixel doesn’t see many changes, and the formula certainly isn’t different. The Pixel 10a isn’t so much a downgraded version of the Pixel 10 as it is a refresh of the Pixel 9a. In fact, it’s hardly deserving of a new name. The new Pixel gets a couple […]
Like
0
Liked
Liked
Online Learning for Multi-Layer Hierarchical Inference under Partial and Policy-Dependent Feedback
Hierarchical inference systems route tasks across multiple computational layers, where each node may either finalize a prediction locally or offload the task to a node in the next layer for further processing. Learning optimal routing policies in such systems is challenging: inference loss is defined recursively across layers, while feedback on prediction error is revealed only at a terminal oracle layer. This induces a partial, policy-dependent feedback structure in which observability probabilities decay with depth, causing importance-weighted estimators […]
Like
0
Liked
Liked