Erfan Mirzaei
@erfunmirzaei.bsky.social
Researcher @PontilGroup.bsky.social| Ph.D. Student @ellis.eu, @Polytechnique, and @UniGenova.
Interested in (deep) learning theory and others.
Interested in (deep) learning theory and others.
🧵Thermodynamics Reveals the Generalization in the Interpolation Regime
In the realm of overparameterized NNs, one can achieve almost zero training error on any data, even random labels, that yield massive test errors.
So, how can we tell when such a model truly generalizes?
arxiv.org/abs/2510.06028
In the realm of overparameterized NNs, one can achieve almost zero training error on any data, even random labels, that yield massive test errors.
So, how can we tell when such a model truly generalizes?
arxiv.org/abs/2510.06028
Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime
The paper provides data-dependent bounds on the test error of the Gibbs algorithm in the overparameterized interpolation regime, where low training errors are also obtained for impossible data, such a...
arxiv.org
November 14, 2025 at 2:11 PM
🧵Thermodynamics Reveals the Generalization in the Interpolation Regime
In the realm of overparameterized NNs, one can achieve almost zero training error on any data, even random labels, that yield massive test errors.
So, how can we tell when such a model truly generalizes?
arxiv.org/abs/2510.06028
In the realm of overparameterized NNs, one can achieve almost zero training error on any data, even random labels, that yield massive test errors.
So, how can we tell when such a model truly generalizes?
arxiv.org/abs/2510.06028
Reposted by Erfan Mirzaei
📢 Upcoming Talk at Our Lab
We’re excited to host Arthur Bizzi from EPFL for a research talk next week!
Title: Towards Neural Kolmogorov Equations: Parallelizable SDE Learning with Neural PDEs
🗓 Date: November 19
⏰ Time: 16:00 CET
📍 Galileo Sala, CHT @iitalk.bsky.social
We’re excited to host Arthur Bizzi from EPFL for a research talk next week!
Title: Towards Neural Kolmogorov Equations: Parallelizable SDE Learning with Neural PDEs
🗓 Date: November 19
⏰ Time: 16:00 CET
📍 Galileo Sala, CHT @iitalk.bsky.social
November 14, 2025 at 2:03 PM
📢 Upcoming Talk at Our Lab
We’re excited to host Arthur Bizzi from EPFL for a research talk next week!
Title: Towards Neural Kolmogorov Equations: Parallelizable SDE Learning with Neural PDEs
🗓 Date: November 19
⏰ Time: 16:00 CET
📍 Galileo Sala, CHT @iitalk.bsky.social
We’re excited to host Arthur Bizzi from EPFL for a research talk next week!
Title: Towards Neural Kolmogorov Equations: Parallelizable SDE Learning with Neural PDEs
🗓 Date: November 19
⏰ Time: 16:00 CET
📍 Galileo Sala, CHT @iitalk.bsky.social
🚨 Poster at #AISTATS2025 tomorrow!
📍Poster Session 1 #125
We present a new empirical Bernstein inequality for Hilbert space-valued random processes—relevant for dependent, even non-stationary data.
w/ Andreas Maurer, @vladimir-slk.bsky.social & M. Pontil
📄 Paper: openreview.net/forum?id=a0E...
📍Poster Session 1 #125
We present a new empirical Bernstein inequality for Hilbert space-valued random processes—relevant for dependent, even non-stationary data.
w/ Andreas Maurer, @vladimir-slk.bsky.social & M. Pontil
📄 Paper: openreview.net/forum?id=a0E...
May 2, 2025 at 6:35 PM
🚨 Poster at #AISTATS2025 tomorrow!
📍Poster Session 1 #125
We present a new empirical Bernstein inequality for Hilbert space-valued random processes—relevant for dependent, even non-stationary data.
w/ Andreas Maurer, @vladimir-slk.bsky.social & M. Pontil
📄 Paper: openreview.net/forum?id=a0E...
📍Poster Session 1 #125
We present a new empirical Bernstein inequality for Hilbert space-valued random processes—relevant for dependent, even non-stationary data.
w/ Andreas Maurer, @vladimir-slk.bsky.social & M. Pontil
📄 Paper: openreview.net/forum?id=a0E...
Reposted by Erfan Mirzaei
1/ 🚀 Over the past two years, our team, CSML, at IIT, has made significant strides in the data-driven modeling of dynamical systems. Curious about how we use advanced operator-based techniques to tackle real-world challenges? Let’s dive in! 🧵👇
January 15, 2025 at 2:34 PM
1/ 🚀 Over the past two years, our team, CSML, at IIT, has made significant strides in the data-driven modeling of dynamical systems. Curious about how we use advanced operator-based techniques to tackle real-world challenges? Let’s dive in! 🧵👇
Reposted by Erfan Mirzaei
An inspiring dive into understanding dynamical processes through 'The Operator Way.' A fascinating approach made accessible for everyone—check it out! 👇👀
For the past four years, I’ve been working on a topic that’s both fascinating and challenging to explain. In this post, I’ve tried to present The Operator Way — a paradigm for understanding dynamical processes — in plain, approachable terms.
pietronvll.github.io/the-operator...
pietronvll.github.io/the-operator...
January 15, 2025 at 10:31 AM
An inspiring dive into understanding dynamical processes through 'The Operator Way.' A fascinating approach made accessible for everyone—check it out! 👇👀
Reposted by Erfan Mirzaei
Excited to present
"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues"
at the M3L workshop at #NeurIPS
https://buff.ly/3BlcD4y
If interested, you can attend the presentation the 14th at 15:00, pass at the afternoon poster session, or DM me to discuss :)
"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues"
at the M3L workshop at #NeurIPS
https://buff.ly/3BlcD4y
If interested, you can attend the presentation the 14th at 15:00, pass at the afternoon poster session, or DM me to discuss :)
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues
Linear Recurrent Neural Networks (LRNNs) such as Mamba, RWKV, GLA, mLSTM, and DeltaNet have emerged as efficient alternatives to Transformers in large language modeling, offering linear scaling with…
buff.ly
December 10, 2024 at 10:52 PM
Excited to present
"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues"
at the M3L workshop at #NeurIPS
https://buff.ly/3BlcD4y
If interested, you can attend the presentation the 14th at 15:00, pass at the afternoon poster session, or DM me to discuss :)
"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues"
at the M3L workshop at #NeurIPS
https://buff.ly/3BlcD4y
If interested, you can attend the presentation the 14th at 15:00, pass at the afternoon poster session, or DM me to discuss :)
Reposted by Erfan Mirzaei
In his book “The Nature of Statistical Learning” V. Vapnik wrote:
“When solving a given problem, try to avoid a more general problem as an intermediate step”
“When solving a given problem, try to avoid a more general problem as an intermediate step”
December 12, 2024 at 5:19 PM
In his book “The Nature of Statistical Learning” V. Vapnik wrote:
“When solving a given problem, try to avoid a more general problem as an intermediate step”
“When solving a given problem, try to avoid a more general problem as an intermediate step”
Excited to share our lab's amazing contributions at NeurIPS this year! Check out our papers and stay inspired! 🚀📚 #NeurIPS2024
At #NeurIPS2024 🇨🇦 our group will present 7 contributions! These span a diverse array of topics: from theoretical advances in stochastic processes and reinforcement learning to applications in molecular dynamics and uncertainty quantification.
December 10, 2024 at 6:18 AM
Excited to share our lab's amazing contributions at NeurIPS this year! Check out our papers and stay inspired! 🚀📚 #NeurIPS2024
Reposted by Erfan Mirzaei
Hi 👋 We're glad to be here on @bsky.app and looking forward to engaging in this community. But first, learn a little more about us...
#ELLISforEurope #AI #ML #CrossBorderCollab #PhD
#ELLISforEurope #AI #ML #CrossBorderCollab #PhD
November 21, 2024 at 10:37 AM
Hi 👋 We're glad to be here on @bsky.app and looking forward to engaging in this community. But first, learn a little more about us...
#ELLISforEurope #AI #ML #CrossBorderCollab #PhD
#ELLISforEurope #AI #ML #CrossBorderCollab #PhD