Deep Learning
SALSA: Attacking Lattice Cryptography with Transformers Emily Wenger University of Chicago Mingjie Chen University of Birmingham Francois Charton
The looming threat of quantum computers has upended the field of cryptography.
Supplementary Material for Chartalist: Labeled Graph Datasets for UTXO and Account-based Blockchains 1 Ransomware Dataset 1.1 BitcoinHeist features On the heterogeneous Bitcoin network, in-neighbors ฮ
On the Bitcoin network, an address may appear multiple times with different inputs and outputs. This window approach serves two purposes. First, the induced 24-hour network allows us to capture how fast a coin moves in the network. The number of blocks measures the speed in the 24-hour window that contains a transaction involving the coin. Second, temporal information of transactions, such as the local time, has been useful to cluster criminal transactions.
Understanding Robust Learning through the Lens of Representation Similarities Christian Cianfarani Department of Computer Science University of Chicago Arjun Nitin Bhagoji
Representation learning, i.e. the generation of representations useful for downstream applications, is a task of fundamental importance that underlies much of
Transformer-based Working Memory for Multiagent Reinforcement Learning with Action Parsing Y aodong Y ang
Our second contribution is to introduce an action semantic inductive bias and implement it with a technique named Entity-Bound Action Layer.
Supplementary Material for Rethinking Value Function Learning for Generalization in Reinforcement Learning A Stiffness Analysis
The green lines in Figure 1 demonstrate that the stiffness decreases as the number of training levels increases in most of the Procgen games. This suggests that the delayed critic update effectively alleviates the memorization problem. Each agent is trained on 200 training levels for 25M environment steps. Each agent is trained for 8M environment steps. The mean is computed over 10 different runs.
Globally Gated Deep Linear Networks
Interestingly, networks with a large number of gating units behave similarly to standard ReLU architectures.
Self-Supervised Learning with Lie Symmetries for Partial Differential Equations
Accurately analyzing and predicting the evolution of such systems is of paramount importance, inspiring decades of innovation in algorithms for numerical methods. However, high-accuracy solvers are often computationally expensive.
